“Oh gosh, it’s late. I need to start getting ready”, she exclaimed.

“Relax! It’s just 7:30. You’re well aware by now that no party ever starts on time”, her husband said, reading the newspaper and sipping his evening tea.

“What should I put on, honey? Do you think the black dress I wore on your birthday would go well?”, she asked as she indulged herself in the pre-makeup work.

“You look way too gorgeous in that dress. Are you sure that’s the one you want to go with?”, he asked still with scant attention on her.

She felt no urge to respond to him. Deep down, this was the affirmation she secretly craved. She needed to be certain that selecting the finest piece from her wardrobe was the right decision that night.

Her mind wandered off to the first time he caught her eye about 2 months back. He wore a navy blue tie on a black suit and radiated warmth that could not be overlooked. He was the senior consultant hired by her startup to work on a project with her.

“Hi, Aruna. My name is Kunal. Nice to meet you!”, he greeted with a cheeky smile as he entered the cabin to introduce himself.

“Nice to meet you too. Looks like we’re going to be working together closely in the upcoming months”, she said realizing how firm his handshake was.

“I am looking forward to it, given your prolific experience in the sector. Yes, ma’am, I did my homework”, he grinned. “By the way, I am a Murakami fan too”, he blurted as he dug through her massive book collection.

That sent butterflies in her stomach in a way that felt wrong.

“Hopefully we will get ample time to discuss these books. Been a long time since I did that with someone, you know?”, he murmured almost to himself.

It got increasingly difficult for her to conceal how her body reacted to his charisma and confidence.

“Hey, you seem busy. I shall take your leave and see you around! Excited to start working with you!”.

She could not utter a word as she was left stunned. You couldn’t blame her. This guy swooped into her office and left her feeling some version of “seen”, perhaps?

“You’re putting in quite the effort for an office party,” her husband remarked, clearly taken aback by her attire.

“Well, it’s a big event and all the important investors are going to be present”, she tried to justify.

The silence that followed drifted her to this one time when they were on their way back from a meeting. Due to his unsettling presence, she made a concerted effort to limit her conversation to work-related matters only.

“Hey, could you turn up the volume? I love that song,” he asked politely from the passenger seat.

“What other bands are you into? Favorite cuisine? What kind of movies do you watch? What did you think of that Black Mirror episode?” He’d pester her with these questions incessantly, whether they were in a cab, on a flight, grabbing a meal, or waiting at the client’s reception.

She attempted to fend him off with curt, monosyllabic responses. The fear of him breaking through her defenses crippled her.

Undeterred, he often responded by posing thought-provoking questions instead. “Do you believe the client’s treatment of their subordinate was justified? Why do you think there are so few women in the workforce anyway? If there was one thing you could do to solve that problem, what would that be?”

These questions got her to start opening up and confiding in him and boy! all the walls she had built around herself came crashing down. After all, she was a sucker for deep or stimulating conversations just like him.

It was a hot Thursday afternoon, they were trying out a new restaurant by the block between their meetings. Anticipation tingled in her veins as she eagerly awaited their lunch break, a daily highlight she cherished. However, as the hour approached, a subtle unease crept over her, a nagging sensation that something was amiss.

She appeared deep in thought. The realization had steadily dawned upon her on how day in, and day out, the routine of work and daily life had quietly strangled her marriage. Loneliness had become her silent companion, especially in the last couple of years. Was it her promotion? Or her husband’s new job which demanded lots of travel? She wasn’t sure.

He caught onto that tension in the air and interrupted her thoughts. “Is everything okay? You look weary.”

“Aah, no. It’s nothing”, She felt surprised that he could notice that. It was as if someone was seeing her again.

“Okay, I won’t probe and make you uncomfortable. But tell me this, how long have you been married for?”

“It’s going to be 10 years this June. Phew! Long time”, she answered a personal question quite comfortably, crossing a self-invented boundary unknowingly. But, there was a touch of melancholy in her voice. “How about you?”

“Well I got divorced 2 years back”, he enlightened her after a slight hault.

“Ouch. I’m sorry to hear that! How are you holding up?”

“Much better now actually. Thanks for asking!”

“Hey hon, how do I look?”, she asked her husband in an anticipatory tone as she finished getting ready.

“You look stellar as always”, her husband complimented without even looking at her.

She contrasted this with the kind of compliments he showered at her. “Did you get a haircut? It really suits you… That dress looks pretty on you… You should wear black more often, it makes you stand out…”

This made her smile. She hadn’t felt this way for a long time. “Why are you smiling, dear?”, her husband looked puzzled.

“Great! Now, he notices!”, she thought to herself and flashed back to their celebratory dinner when they won the big deal together.

“Hey, congratulations! You kicked some ass back there. You were on fire. I mean we have to celebrate the deal”, the zeal in his voice was evident.

“Thank you, that means a lot! But, I can’t. I will get home late!”

“I never insist, but come on! Just this one time, because today calls for a real celebration. Just a nice meal and maybe a beer!”, he pleaded.

“Alright alright”, she grinned.

“Honey I am going to be late tonight..going for dinner with a colleague. Don’t wait for me”, read the text she sent her husband.

After 3 hours and 5 beer bottles down, he suddenly found himself lost in thoughts, questioning why fate hadn’t brought them together a decade earlier.

He started fabricating stories about how he would have asked her out, the amount of fun they would have on movie or theatre dates, dinners, or music shows — you name it! He would have shown her his favorite spots in the city, specially handcrafted for gorgeous sunset views and she would have shown her how she decorated her apartment perhaps?

But it didn’t matter. It was too late. It took every ounce of strength in him to accept that she couldn’t be his. He felt fortunate to have met her, learned many things, and created memories of chatting, joking, and debating with her.

He gave her this intense, very soulful stare. “What?”, she retorted.

“Your husband is a lucky man you know”. There was remorse all over his face.

“Well, I don’t think he feels that way though..But I have to thank you…I have had the most fun the last two months. Sorry if I came across as too secluded and reserved at the start”, she was careful not to divulge too much about the state of her marriage, having gulped two beer bottles.

“Don’t apologize. I could always understand It’s not easy being a woman in business, running such a huge and talented team.”

She looked at him affectionately and felt very warm and fuzzy in her heart.

“Am I attracted to him? That’s not possible! Who even gets attracted at my age to someone else? He’s just a dear friend!” she quickly dismissed these thoughts and decided to delight in all her naivety.

“It’s late! I should head home”, she uttered hastily to ensure no boundaries were crossed that night.

“Let me drop you home. You obviously can’t drive in this state.”

She made a rebellious face.

“No, don’t debate me on this”, he chided her.

“Only on one condition”.

“Shoot.”

“Next time, I am gonna decide the place.”

“Haha. Give me the keys”, he supported her as she walked towards her car.

After a lot of fun banter in the car, he parked outside her apartment and confessed, “Thank you for showing me such an amazing time tonight. I loved it! It’s hard to acknowledge how time passes by with you.”

She blushed and waved him goodnight.

“Nothing honey.. just got reminded of an incident from a get-together with colleagues”, she tried her best to sound believable.

“That’s strange. Why haven’t you told me about it?”, he asked.

“Ummm.. I don’t know. We haven’t gotten adequate time to speak properly lately”.

“Yeah, I know. I’ve been swamped with work. Today was one day I was free but your office party randomly sprang up!”

“You have been occupied for weeks now and this is that one night when I am engaged and now you’re blaming me?”

“I know. I am not blaming you. Let’s go out for dinner this weekend?”, he proposed and let out a long, deep sigh.

“Sure, but promise me you won’t cancel at the last moment like the last four times”, she interjected, arranging the handbag she would be carrying.

She was reminded of one of those weekend plans with him as she went to the garage to get her car out. It was one of those gloomy Saturday afternoons when her husband bailed on her again.

Her phone vibrated as she was watching TV. “Hey. What you doing tonight?”, his text read.

“Nothing much. My husband is out of town. The plan is to chill on my own, maybe read a bit”, she tried to sound nonchalant but was relieved to see his messages.

“I have two tickets for this exotic play. Want to give me some company?”

“Sure. Sounds interesting! When is it?”

“This evening. Will pick you up in an hour or so.”

She was glad to escape from the fact that her marriage had plunged into a mid-life crisis and engage in something rather interesting — a topic such as feminism and masculinity in the modern world, which was what the play was about.

Her heart raced with each passing minute behind the wheel. She couldn’t wait to see him.

“Hey”, she whispered staring at him from a distance.

“I thought you won’t show up.”

“Wait, What? Why?”, she sought an explanation.

“I just assumed you’re not good with goodbyes.”

“Goodbye?”, she inquired in shock.

“My work here is almost done. I leave the city this Sunday to start a new project next week”.

“What?!” That was rather a scream. “Wait.. what?”, she repeated.

“I thought you knew. But if it makes a difference, I wish I didn’t have to.”

She was speechless. She tried to disguise her tears under the glamour of her makeup hard but her efforts went in vain.

“Hey. You alright?”, he handed her his handkerchief. pouring her a glass of water. “Let’s find a place that doesn’t have a flock of people.”

They walked over to the rear side of the building near the foundations and he just sat next to her and tried to comfort her by rubbing her shoulders. She just sat in silence, trying to process these complex feelings that erupted inside her.

“No pressure, but in about an hour you have your speech coming up, so we have to get you all ready by then…But, I have something I’d like to share, now that I’m leaving. The only reason I didn’t so far is because I thought it was inconsequential”, he smiled wistfully.

She nodded.

“There hasn’t been a day I haven’t thought about you.” He paused for a couple of seconds.

“I know it’s wrong. You have your life here and I’m still figuring my place after my divorce. I know we haven’t spoken much about those parts of our lives. But, don’t worry, I have accepted my fate and have no expectations from you, only gratitude”.

“You’ve made me feel things I haven’t felt in a long time, you made me feel alive again”, she admitted.

“What if I tell you I felt those things too?” He gazed deeply into her eyes and found a wealth of unspoken emotion.

“Don’t go?”, she made a humble request.

“You know that’s not possible”.

He came so close he could smell her hair and tucked her hair behind her earrings.

“Oh! You’re so beautiful”, he brought his lips close to hers.

10 years of marriage. 3650 days of hard work. 87600 days of sweat. 1 moment of weakness. 1 chance to be young again. 1 more strong rush of adrenaline. What is she going to choose?

What would you choose?

The Dilemma: What is she going to choose? What would you choose? was originally published in Sine Waves on Medium, where people are continuing the conversation by highlighting and responding to this story.

“Back in the bad old days of traveling circuses, elephant trainers would shackle baby elephants to stakes using large chains. At first, the elephant would pull and pull, but would eventually give up. Over time, the trainers were able to reduce the chain to a rope, and eventually to an even smaller rope. The elephants, believing they couldn’t escape, never tested if they could break the bonds.” — Lloyd Tabb, CEO Looker

TL;DR

Today, we launch and present to you: Locale.ai! Use this link, you choose your industry and your job role and experience what Locale has to offer for your business.

Locale’s Premise: I Locate, therefore I Operate

In 2009, when Mixpanel launched, their pitch was — In this user-centric era, the most successful companies are the ones who understand how their users behave, what they interact with the most, why they come back, and why they leave.

This pitch definitely worked because it led to a massive change in behavior. A decade later, marketers and growth teams in every web or mobile app company, take data-driven decisions and keep experimenting to personalize the user experience.

But what about the city and central ops teams in companies that have ground operations?

Having access to localized insights on user movement, fleet performance, delays, and shipping costs should be as easy as it is analyzing user behavior on apps. However, that’s not how it works today!

Because the real world is far more fickle and chaotic, it becomes even more challenging to deliver to users as soon as possible, utilizing assets on the ground in the most optimum manner and maximizing the efficiency of your workforce.

At Locale, we are going long on these companies helping them decipher this world. Thankfully, with the help of GPS tech, companies are collecting a lot of location data than ever before! But geo location is still a very under-utilized asset today in all companies. After all, only ~7% of the location data gets used for analytics!

Why Go Hyperlocal?

If you are a company with hyperlocal supply chain operations, its imperative for you to reduce user churn, improve unit economics and become operationally efficient.

However, it’s quite impossible to improve these metrics without going very granular within your city across all your verticals- demand, operations and supply. Going granular helps you debug bottlenecks in your operations and find the right areas and opportunities to focus on.

Just like you create user cohorts depending on their behavior and provide personalized experiences, promotions and messaging to each cohort- Similarly, areas also have properties. Depending on the properties that areas show, you can experiment with customized strategies and see what works in different areas.

The Status Quo: Everyone Ends up Losing!

“We can’t spare developer time right now.”

That’s what you’ll hear if you ask companies why they don’t have visibility into their supply-demand gaps, delays or why they are not tracking how different strategies.

The current process ends up being extremely painful — Data would be imported from the warehouse or analytics engine like Clevertap, transformed in R or Python, downloaded in the form of Excel Sheets and visualized on Kepler.gl!

Upon speaking, interviewing, and working with a countless number of companies, here is what we learned:

• For almost every vertical in a company, there exist SAAS products (HR, Marketing, Accounting, Sales) but nothing much really for operations or logistics teams!
• Most of the operations (even in the leading tech companies) still use Excel Sheets to analyze metrics at city levels and have a “mental map” of how areas are distributed in the city!
• Product managers and decision makers depend on an analyst to get values of a metric which takes anywhere between 24 to 48 hours!
• Live internal dashboards for product managers often take a sprint of developer’s bandwidth and they are often built as a one-off use case.
• We have spoken to data scientists who felt more like a “reporting team” because 90% of their job was about calculating geospatial metrics!
• Due to all these reasons and the internal tools not being well-maintained, a lot of operational decisions end up powered by the intuition of ops and city teams.

The geospatial industry’s innovation cycle simply hasn’t kept up with the rest of the data and tech space. Where are the tools for the new generation of tech-savvy geospatial data experts? Why has an innovation cycle been missed?

Hence, we built Locale.ai!

Over the past 15 months, Locale was specially built for companies that have supply chain and hyperlocal operations. Our target industries include ride-sharing, hyperlocal delivery, logistics and supply chain and app-based workforce.

We get in all your location data that is segregated across your marketing data (user events), operations data (supply pings) as well as trips data (transactions) into one place and give you precise insights at scale. Our aim has always been to empower decision makers and CXOs who don’t have time to write code or don’t prefer writing SQL with localized insights.

With Locale, you can drill down from “city” to “a single order” in two clicks without depending on any engineering favors. Whether you need real-time insights for your tactical decisions or want to go back in time for historical analysis, we have got you covered!

“Locale enables us to look at our business in a completely new way. We now have visibility on our demand, supply and operations from the city down to each building. We love the depth of insights Locale provides.”- Co-founder, Hydrop

Use Cases

How we didn't build a product until 6 months in our SaaS Journey

Several rounds of iterations led us to this version of the product that we are proud of! Fun fact, you can read more about our journey here:

Here are some of the ways in which we can help different teams with their decisions:

Marketing and Growth

• Acquisition: Finding out the right areas to acquire users based on already existing latent demand.
• Conversion: Debugging the reasons for user drop-off right before booking across different areas and incresing conversions.
• Retention: Doing very targeted hyperlocal promotions using user order patterns or doing route-based promotions for mobility users.
• Impact Analysis: Measuring the conversion via different offline advertisement avenues in different areas.

City and Central Ops

• Monitoring Operations: Monitoring key metrics in real time and getting alerted in case of anomalies. Also measuring business health across all verticals and areas.
• Demand-Supply Gaps: Evaluting the gaps in supply re-distribution to ensure high booking fulfilment.
• Revenue vs Cost: Improve topline by analyzing the revenue vs cost (time taken or distance traveled to rech destination) in different areas.
• Inventory Analysis: Analyzing inventory shelf time, damaged or returned at different warehouses.
• Cancellations: Analyzing cancellations patterns and reasons across partners, couriers and users in different areas.

Strategy and CXOs

• Movement Patterns: Finding out how your power users move in the city and where they go.
• Cost of Shipping: Readjusting the price or delivery feesMeasuring the true cost of shipping to users in different locations.
• Delay and SLAs: Understanding which deliveries, routes, partners or couriers cause delays and due to whcih lap of the journey.
• Productivity: Measuring fleet performance and rewarding the top performers or incentivizing the bottom ones.
• Courier Performance: Analyzing the performance of all 3rd party logistics companies across SKUs in different areas.

If any of these use cases resonate with you, you can log into the product, select your industry and your job roles and experience all that Locale has to offer- and understand how Locale helps in solving for these problems by showing very precise, localized insights.

Access the demo link here.

So, why give us a shot?

The most successful companies that have some kind of ground operations have a deep understanding of their business health on ground and that makes all the difference. They know everything from how much demand is going to come from this location ( Uber) and allocate supply accordingly, or price stays not only as per user’s destination but also the place of booking ( Airbnb).

“We were silently losing money on shipping but were not capturing that data because we lacked precise visibility into our true cost of shipping i.e. fuel adjustments and post-shipping accessorial charges. After Locale, we updated our shipping charges in real-time, so we can maintain our margins and best serve our customers.”- Praful Mathur, Co-founder, VNDR

We have worked very hard to ensure that we make your experience of working with maps and taking hard operational decisions delightful. We want to take all the unpleasant grunt work away while you work on your core business challenges.

We have seen some impactful results with the companies we have been working with. Here’s a case study with India’s largest scooter sharing company for you to delve further:

How India's Top Scooter Sharing Player Used Locale.ai to Reduce User Churn by 9%

Locale is the fastest route to attain operational excellence using your location data. There’s a lot more to it and we encourage you to try us out as there’s so much under the hood. Our aim is to support you in what you do best — delivering magic to your customers irrespective of the location, time, day or weather!

Originally published at https://blog.locale.ai on August 26, 2020.

TL;DR

We have launched finally and you can find our product and are proud to present to you: Locale.ai! Use this link, you choose your industry and your job role and experience what Locale has to offer for your business.

I have always felt that a product launch is like a marriage proposal- you want a positive response, you’re scared of a failure and you are nervous about everything. That makes the pre-launch like preparation of the proposal.

But this preparation also gives a good excuse to sit and reflect through this one hell of a journey with all its ups and downs, sometimes all in a day. And also to express gratitude to everyone who has helped us in any small way to get here- especially our team members, to whom we dedicate this piece.

Taking the Plunge

A very common question thrown at me is, “How did you come across this idea?”

My friend and now co-founder, Rishabh had lived through this problem first hand. At SocialCops, Rishabh had worked on a wide range of projects with Government Ministries, FMCGs, startups and supply chain companies on different business problems related to location.

While Rishabh himself had to build quite a number of internal tools for his day-to-day workflow, we also realized that companies of all shapes and sizes are collecting a huge amount of location data and they themselves didn’t have right products to leverage this data. Often, they had to build internal products which were extremely painful to use as they were not well-maintained.

It was then we started asking ourselves questions like- “Why do companies need to come to us to crunch their data and solve their problems? Can we build a product to empower local teams inside these companies to solve at least some of these problems on their own?”

“Right now, to get any insight, I need to depend on my analyst teams to write queries- A process that takes 24 hour to 48 hours. To get a live dashboads, I need to depend on my engineering teams which usually takes a sprint.”- PM, logistics

We then set out to validate this problem: We spoke to around 50 companies or so all over the world asking them all kinds of questions about what insights they use from their location data, which tools do they use and what kind of decisions they took. Their answers gave us the much-needed confidence we were looking for!

And that’s how the journey started, both of us, packed our bags and moved to Bangalore with this vague problem statement in our mind and a head full of dreams.

March 2019: The Birth of Locale.ai

This desire to fix this “problem” led us onto a journey that gave birth to “Locale.ai”. The journey was, and continues to be an emotional roller coaster: we question ourselves every day and that is what I love about our journey- the questions it makes us ask.

It is a common misconception that starting up is the hardest part there is, but I’m sure that any entrepreneur who has built a business will agree that starting up is by far the easiest piece of the puzzle. What comes ahead are the biggest hurdles to an entrepreneurial journey- the team building, reforming the product for the ideal user profile, and dealing with rejection.

Lap 1: Conceptualizing the v1 of the Product

While those customer calls gave us confidence in the problem, we were still clueless about the solution. So, there was only one way to find out — We demoed our prototype to some leading on-demand and mobility companies in India with that we bagged our first set of small PoCs.

These PoCs gave us an excuse to sit in their offices, brainstorm and interview our potential users. After all, we still had to find answers to questions such as- “What’s the real problem? What’s the current solution? What’s the product going to be? Who would be the target user? How do we position it?”

To make these analyses, companies required engineers to create custom-made dashboards. But this approach to create internal tools came with two problems- the engineering team spent a lot of time and resources in creating these dashboards and the dashboards that were in use were not scalable. We learnt that companies wanted such a tool that business leaders could use to visualize the data regarding their on-ground operations instead of having to rely on answers to queries sent to the engineering teams.

“We were silently losing money on shipping but were not capturing that data because we lacked precise visibility into our true cost of shipping i.e. fuel adjustments and post-shipping accessorial charges. After Locale, we updated our shipping charges in realtime so we can maintain our margins and best serve our customers”- Praful Mathur, Co-founder, VNDR

While we were ready with all our answers to build our product, we now needed a team of engineers but were running out of our savings. We needed money and we needed to fundraise. The fundraising journey was a whole new ballgame in itself and deserves a chapter of its own. Here is a synopsis:

A lot of people have recently reached out asking questions and advice on fundraising. So I am compiling a thread on my experience as a first time entrepreneur. 1/10#startups #funding #fundraising

After a long, draining journey we were fortunate to have Vaibhav from Better Capital as our lead investor along with Pallav, Raveen and Steve as our angel investors.

[Funding alert] Location analytics startup Locale.ai raises undisclosed amount from Better Capital and angels

Postponing the First Launch

While we started building our core team of engineers to start working on the product, on one hand, we started working on positioning the product. Throughout pitching to customers, investors and advisors, we got asked to questions like- Why this focus on geo-location? Why a different product for location analysis? Are you building a BI for location data? Isn’t this very core to companies?

Our challenge was that companies, especially in the logistics or delivery sector, hadn’t seen a product like this. And some startups who were using open source tools knew the importance of something like this but asked us- “Why shouldn’t we build this internally?”

So, in order to clear these doubts, we always knew the best way to go about it would be to let the product speak for itself. In other words, launch the product such that anyone from our target industries could get a feel of the product to comprehend the value. We assumed it would take us a month to build the end-to-end product along with real-time pipelines. And then, reality hit!

We seriously underestimated the time it would take us to build the pipeline that can handle three different kinds of data: marketing data (user events), operations data (supply pings) along with order data (transactions) — all of this in real-time and at scale!

Lap 2: Iterations. Iterations. Coming up with the v2

Fast forward, it took us roughly 3 months to build the first version of the working product. With this, Locale became a canvas for our users: they could create different metrics and consoles mixing and matching data across databases and get insights on their ground performance.

When we deployed the product for India’s fastest growing scooter-sharing company, it was then it became clear to us that our users (city, ops and growth teams) did not understand what to search for and what to measure since there was no steel structure that guided them. (A part of this was of course the bad UX!).

We learnt that if we launch the product in this shape, people may still not get the value since we won’t be there working closely with them to depict what all they can do with Locale. It was as if we had built a city but the visitors needed a tour guide to travel through the city and help them reach their destinations.

And with this, we extended our launch yet again and went back to the drawing board.

Side Note: Here’s how they used our product to open their stations (hubs)

How India's Top Scooter Sharing Player Used Locale.ai to Reduce User Churn by 9%

“Locale taught me that it doesn’t matter who you are or where you come from, what matters is if we all are equally passionate for the problem. When you believe in a problem and are passionate about it, everything else takes a backseat.”- Anubhav Pattnaik, Content Team, Locale

Shaping v2’s Structure along with the Philosophy

What we did was pick up our target industries and wrote down the list of top decisions for them and map each of those decisions to metrics. For example, we ended up understanding the most important questions that a business team in a delivery company could ask were built around understanding demand-supply gaps, or where users drop off, or where they should shoot promotions.

The journey to overcome this challenge led to the birth of a set of analyses. Every analysis or screen of the product is composed of the top metrics that leads to a decision, thus making it very actionable for our end users.

While we got down to building this, we also started our cold outreach again and demoed this new product concept to our prospects and received tons of feedback. We used the top rejections we got and try to engineer a solution to combat that into the product.

I remember the days when I used to play around with QGIS and how complicated it felt. Building a geospatial platform for the web is hard and challenging because it demands to be accessible to cater for a wide range of user bases and devices. It’s sure is difficult, but we proved it to be not impossible ✨- Musthaq Ahamad, UX Engineer, Locale

Lap 3: The Grand Launch of Locale

Now, after 15 months, 1000s of burning the midnight oil with a team of 7, we feel we are ready to present Locale to the world!

As a visitor, you can now log into the product, select your industry and your job roles and experience all that Locale has to offer- all the decisions and problems Locale can help you with its consoles and analyses.

We are extremely excited to welcome you, dear reader, to join us on this journey as we try to solve the mysteries of the geospatial world. We have one simple goal- to help you measure every location aspect of your business and make you operationally efficient.

We learnt countless priceless lessons while we were on this journey but if we just had one lesson to share with y’all it would be:

“Like Niel Gaiman said, Keep Making Good Art”- Rishabh

Read our launch blog here:

Launching Locale.ai: Operational Analytics for Hyperlocal Decisions

Originally published here on July 23, 2020.

Co-authors: Himanshu Thakur, Nikhil Gupta

Key Takeaway:

In this blog, we will discuss how you can use Locale.ai to analyze Irys mobility data for different use cases by overlaying it on top of your internal data. The data is collected & curated from geolocation signals using millions of connected devices worldwide. We also did some data-cruncing to show you mobility insights during the lockdown period in Bangalore, India.

What is external data and why should you care about it?

Often, internal data that is genearted and owned by the company (like customer’s transactional data, user events data on websites or apps, vehicle sensor data, data from workforce apps) doesn’t provide the complete picture, especially for companies that are expanding in newer locations or for those who don’t possess rich internal data.

External geospatial data streams refer to data that can be found and collected from external sources. These might be publically available or are collated and sourced by various organizations.

Why Mobility Data?

Human mobility plays a great role in uncovering human behavior patterns and individual habits. Human mobility can help to have insights on spatial distribution on movements, creation of user personas, use of public transportation, level of walkability, and pollution emission in a region. The data sources of human mobility data are GPS data, cell tower data, and WiFi data.

“How people move and where they go tells you about who they are.”

Why is Irys’s external data useful and why should you use it?

To work with human mobility data, we turned to Irys — a location intelligence company that specializes in transforming human mobility data into powerful insights for businesses. Irys has one of the largest corpuses of anonymized mobile GPS data spanning hundreds of millions of devices across 150 countries.

Mobile GPS data is the gold standard for mobility data due to its excellent coverage of device behavior and high location precision. This makes it ideal for capturing the intricate dynamics of places and people at varying resolutions. Irys uses sophisticated models to extract information that describes everything from the small (single store or city block) to the large (big populations, neighborhoods, cities, and even countries).

Here are examples of how customers across different industries leverage this data:

• Property Valuation: Real-estate buyers use property insights to assess the potential performance of new deals and acquisitions.
• Benchmarking Retail Performance: Brick-and-mortar retailers use retail traffic to understand how their locations perform against the industry and competitors.
• Targeted Advertising: Marketers ingest visitation data to identify and target consumer segments based on the types of places they visit.

The applications are endless, and we were very excited to work with Irys and explore new applications in logistics and planning for our customers.

• Expansion: Irys data is useful for any kind of expansion. Whether it is a ride sharing company looking to set up a new station, or a cloud kitchen company looking to open a new center or a bank planning their new branch.
• OOH Advertising:This data is also useful for out of home advertising (to pinpoint locations of setting up bilboards) on the routes most traveled.
• Sales & Distribution: The datacollected from smartphones is a good proxy for penetration is that area along with economic growth. Often, FMCG and real estate companies use it to identify the areas they need to do more targeted sales.

Locale- Irys Console and Insights

In this section, we want to show you some interesting insights that we got after lots of data crunching. We were able to pull off a console that shows how people move across the city of Bangalore, India.

The data spans the entire month of March 2020 and shows how subtle changes have occurred in the city, right after India went under lockdown n 24th March.

A bird’s eye view of the console is enough to spot the huge dip in the number of people moving across the city. As evident from the timeline, there was a sudden drop in the number of people moving on 22nd March, then a spike on 23rd March and then a final dip from 24rth March onwards. But what was so special about 22nd March?

It was the same day when the PM asked billions of Indians to stay at home under a short campaign, popularly known as “Janta Curfew”. Following this, the lockdown was announced on 23rd of March to be in effect from 24rth March onwards. But what can your business take away from this? Let’s find that out by looking how lockdown affected industries and daily business operations.

Let’s filter to a week before lockdown. With around 18k unique people across the city, the average distance which they traveled was roughly 3kms. Also, the map makes it very clear the left part of Bengaluru is not active as the right one.

Now, let’s see how a week after lockdown looks like.

At a glance, we can see that the total number of unique people moving across the city has become half to ~9k and the average distance which they cover has become one third to 0.9kms. Also, certain parts of the city have seen a drastic fall in the total number of people moving in and out of those areas.

A closer look at the highly-dense areas reveals another interesting thing about the change.

Most of the activities post lockdown confined to the upper right area or Bengaluru east, although the intensity is still very low compared to the pre lockdown period.

If you are a decision-maker, you can now see what areas are badly hit and define strategies to make each area of the city more accessible. Certainly, lower bengaluru seems to be hit badly or has movement restrictions in those areas.

So, if you do deliveries, you can make use of this insight to plan your delivery partners to comply with regulations, improve ETAs by factoring in reduced traffic, etc. For a ride hailing company, this insight means now you can allocate resources into the right hotspots where people really need to move.

How Locale.ai uses external data to power their analytics?

One of the biggest challenges of external data is that it is difficult to find and access for teams everywhere. From the time they start searching for data, find the right vendors, test samples, go through the legal and finance process-it takes four-six months.

At Locale, we’re making it extremely easy for you to access and enrich your internal data with external data in minutes, not weeks or months. From our data marketplace feature, you can quickly select datasets and experiment with the ones that are the most relevant to you.

The best part is that the data will already be cleaned and processed in our marketplace module and we do the heavy lifting for you. What’s more, you can access this data at an extremely granular level-at least 10 times more granular than traditional ward-level data. This helps you make more targeted decisions for your business and get better returns on money spent on sales, marketing or other activities.

If you want to know more, check out Website or reach out to me on LinkedIn or Twitter.

Originally published at https://blog.locale.ai on June 30, 2020.

Localize your matching algorithm according to how your demand and supply behave in different areas

Note: Before reading this piece, I highly recommend you reading the first part of this series which covers the basics of supply-demand analysis here:

How Mobility Companies can increase Asset Utilization Geospatially

Ordering food, groceries, cigarettes or even booze at the tap of our phones has become a norm these days. And if you are like me, you probably order everything at the oddest hours of the day!

For an on-demand company (aka “Uber for X”), that is primarily a three-sided marketplace, matching demand and supply is at the core of the business and also extremely challenging. Moreover, the real-world introduces far more variation that leads to starker results than in the model.

When supply-demand gaps exists, we are either losing orders or our riders are idle — both of which are contributing to losing money. But, what’s causing these gaps to exist? This could happen as a function of demand, supply or both.

Case 1: Demand

Lost Orders

The number of orders that you are losing with time because the riders are not available or they are present in the wrong location.

Order Velocity

When you are losing orders, how does the order velocity look like? Which means are you getting more orders or lesser orders than usual?

Case 2: Supply

Idle Riders

The number of riders that are idle and the amount of time they are spending without being utilized because of the wrong location or lesser demand.

Note: Being idle is a point in time property. Hence, while analyzing historically, we need to analyze the metric “idle session time”.

Total Supply Available

When riders are idle, how does the availability of the total riders look like? Have the number of available riders increased or decreased? While analyzing this historically, we need to analyze the metric “total session time”.

Decoding the Reasons for the Gaps

Before even trying to bridge the gaps, we need to understand “why” they are happening in the first place. If the orders are getting lost it might be due to the following reasons:

Riders are not available

• Wrong Location: If we are losing orders, it might mean that the riders are not available which means they are either all busy or are idle in the wrong location.
• Excess Supply: There can also be a case where we are catering to all the demand but have excess idle riders. It might be worth analyzing the total available supply then.

The order frequency is falling

If the frequency at which you receive orders on that day and that time is lesser than the usual, that means you need to dive into why that’s happening.

• Type: Is it all types of orders or only a particular kind of order? For example, is it only category A which is falling which contributes to the majority of the order volume.
• Lifecycle: Is there a particular step in the order journey which is seeing a huge number of drop-offs? For example, are there some challenges with the checkout system or the payment gateway due to which users are not able to complete their orders?

Orders are not being allocated

There might be a possibility that orders are coming in but they are not getting allocated to the riders. If this is happening, there might be some problem with the allocation (or matching) algorithm that you are using. In these cases, it is best to raise this concern with the relevant people inside the organization.

In a three-sided marketplace, sometimes there might be an allocation problem with the store or the restaurant. I myself have experienced quite a number of cases when I couldn’t receive the order because the issue was at the restaurant.

To delve deeper on how to carry out analyses on static location such as stores or restaurants, check this out:

Optimizing the Performance of Static Locations Geospatially

Riders are not accepting the orders

Let’s say that the orders are being allocated to the riders but they are not accepting the orders. This might happen because of a number of reasons.

• Distance: Are they not accepting the orders because the distance to pick up is very high?
• Area: Are they not accepting the orders because they don’t wish to travel to the location of the pickup?
• Payment: Are they canceling because the payment mode of the user is not preferable?

Riders are canceling the orders

Often, all of us have experienced riders canceling the orders after they have accepted it — especially once they get to know about the drop location.

• Distance: Are they canceling the orders because the distance to dropoff is very high?
• Area: Are they canceling the orders because they don’t wish to travel to the drop location?
• Origin-Destination: Is it neither about the origin or the destination but about the route? In that case, large incentives also often don’t work because riders just don’t wish to cross those areas.

Cities usually have invisible walls that riders prefer not to cross. Where are these walls? What times of the day are they most prominent in?

Flows

As discussed before, supply-demand matching is not just about what’s happening right now. It’s about the flow. Where is demand going to be next and how does it move in different days and different times?

Understanding flow for last-mile delivery companies is super important. Which area is the most likely to get demand next? How far is that from where the drivers are currently?

For example, with one of the last mile delivery companies, studying the flow showed that the delivery partners started moving towards the center of the city and by evening, they started moving out, because most of them lived on the outskirts. But they needed to come inwards because that’s the region in which they receive the maximum amount of orders.

External Insights

• Points of Interest: Another very interesting analysis that can be done is to analyze how the supply-demand gets influenced by different points of interest such as schools, colleges, malls or tourist destinations.
• External Events: It would also be insightful to analyze how different external events such as rain, a large concert, a sports match, protests affect the demand and the supply for your company.
• Cohorts: A cohort is a group of users, riders or bikes that perform similarly. What kind of users and order do I lose at different times of the
• day and days of the week? What kind of riders is idle most of the time?

About Locale.ai

Locale is a location analytics platform, which means we convert your raw lat-long data across all databases and formats into meaningful insights so that decision-makers can make very precise, data-driven decisions about their ground operations.

Web analytics tools already help you improve these metrics, using clickstream data. However, with companies that have moving assets on the ground, not looking at things geospatially can be extremely detrimental!

At Locale, we are creating examples of companies who are improving their unit economics, cost per delivery, utilization by doing geospatial analytics. If you are a growth manager looking to improve user acquisition, retention, and conversion, then get in touch for a demo here or get in touch with me on LinkedIn or Twitter.

Originally posted here.

Similar Reads:

• Carto vs Kepler vs Locale: Which product to use for geospatial analytics?
• How to Improve User Acquisition & Conversion using Location Analytics

What does Supply-Demand Gaps Mean for On-Demand Delivery? was originally published in TDS Archive on Medium, where people are continuing the conversation by highlighting and responding to this story.

Key Takeaway

If you are the manager of a ride-hailing company then this piece is for you. Read this blog to understand how you can use location analytics to acquire more users, identify bottlenecks in your booking process, track your movable vehicles, and increase profitability as a whole.

Introduction

First things first: Why should you read this piece? Or, a better question: Why is it important to visualize your metrics on a map?

Because if you are a company that has moving vehicles or has operations in the physical world, a lot of your decisions involve an element of “where”.

Whether it is your users, or bikes, or cars, that is moving on the ground, analyzing metrics that are affected by their location is critical. My favorite example that I like to quote is Uber’s surge pricing model that we all have paid at some point in our lives.

The surge value is influenced by the supply-demand gap at the location where you are booking. In order words, what is the demand density in your area and how much supply is available to cater to the demand along with other parameters such as time, day, weather, traffic, city and so on.

Side Note: In case you want to delve deeper into Uber’s pricing model, check this out:

How does Uber do Surge Pricing using Location Data?

But, the question remains: Why it is important to analyze metrics by location? Why do we need to think of location as an additional parameter?

Every location has an inherent property of its own and therefore, our decisions and strategies need to take that “context” into account.

Critical Metrics for Ride-hailing Companies

Ride-hailing is a term to describe booking rides and paying for car service through a smartphone app with a transportation network company (TNC) such as Uber, Lyft, Ola, Grab, Go-Jek, Rapido, Careem.

In this section, we will deep dive into what are some of the most influential metrics for ride-hailing companies. Which geospatial distributions on a map makes the most sense for them?

Users Events: [Marketing/Growth teams]

• Installs: Where are people installing the app? Are you currently servicable in that area?
• Searches: Where are users searching for a ride? Do we have drivers in those hotspots? if not, how far are they?
• Bookings: Where do bookings take place? How long after the user searches for a ride? What is the booking frequency?
• Trips: Where do trips take place because of promotions? Where do discounted trips happen?
• Cancellations: Where are trips canceled by the user? Do they cancel because of the ETA?
• Churn: Where do people search but don’t book? Which step do they drop-off? Is it because they don’t get the right preference for the car or is it because of the price?
• Cohorts: Where do we get repeat customers from? Where do we get the most valuable customers from?

Driver Metrics: [Supply/City Teams]

• Total Supply: What is the total number of drivers & how many of them are off-duty or full-time drivers?
• Busy or Idle Driver: How many drivers are idle or busy right now? [This is only useful in real-time] How far are they from the area where we would get demand?
• Idle time or Busy Time: Where do partners spend the most amount of idle time? [This is useful historically] How far are they from the next demand hotspot?
• Cancellations: Where do drivers cancel the bookings? Is it because of the drop location or mode of payment?
• Earnings per Hour or Incentives: Where and when do drivers make the most amount of earnings or incentives?

Trips: [Strategy/Growth Teams]

• Trips Start: What are the most common types of pick up points? Which of them are repeatable? Where do power users start the trip from?
• Trips End: Where do the largest distance trip end? Where do long-duration trips end?
• Origin- Destination Pairs: What are the top O-D pairs in a city? What are the top O-D pairs of most profitable trips?
• Paths: What are the most common paths that repeatable users take?
• Flow: Flow analysis (or network analysis) is to understand how the city moves at different times of the day or even historically.
• Idle Spots: Where are the most common spots where drivers are idle while in trip?
• Walls: Every city has these theoretical “walls” or the combination of origin-destination that drivers don’t prefer to cross.

Business [CXO / Decision Maker]

• Revenue: How is revenue distributed in a city? What are the lowest revenue but the highest driver cost areas?
• Driver Utilization: How is driver utilization spread across city and how does that change with different times of the day?
• Total Kms Driven: How many kilometers have been driven? How is that spread across unique users and trips?
• Requests per hour: How many booking requests do we get per hour in different areas?
• Conversion Rate: What’s the conversion rate of those requests in terms of rider acceptance? Where and when do riders don’t accept bookings?
• Completion Rate: What’s the completion rate of the trips started?

Operations: [Operations/City Teams]

• Accidents: Which areas are the most accident-prone? What kind of behavior causes it?
• Frauds: What are the areas where drivers commit fraud? Refunds from the user’s side are where a lot of fraud happen, especially when they report of driver not reaching the right pick up location.
• Safety: What are the areas or routes which are not reported safe either for users or drivers?

Build vs Buy: How do you choose?

Locale.ai is a location analytics platform, which acts like your control center taking your marketing, supply, and trips data into one place to give you very precise, real-time insights.

Building it Internally

While working with some of the leading on-demand and micro-mobility companies, what we observed that they end up hacking around these open-source tools like Kepler itself or QGIS.

Sometimes developers also build their own internal tools, but most of the time they are not well suited for all different audiences inside the company and since the tools are not built in a scalable way, maintaining these suck up a lot of their bandwidth often!

A lot of times there is even a repetition of effort and the wheel keeps getting re-invented over and over again. As Jeff Lawson from Twilio said -

“It is easier than ever to build software but harder than ever to operate it”

Why Choose Locale.ai?

So, if you are a company that decides to build this internally, it would have to be built like a platform itself, (much like how Uber has done it) and with the following characteristics:

• Simple and intuitive user interface to carry out analyses, especially for business users
• Scalable geospatial visualizations with actionability
• ETL robust enough to handle streaming data as well as historical analysis to go back in time

This would require setting up a team of at least 6–7 (consisting of the front end and data engineers, geospatial analysts as well as data scientists). On top of that, the added pain of waiting for at least 6 months to build the platform and kickstart the analyses.

If you want to delve further, check our website out or get in touch with me on LinkedIn or Twitter.

Read Similar:

Carto vs Kepler vs Locale: Which product to use for geospatial analytics?

Originally published at https://blog.locale.ai on May 17, 2020.

Co-author: Rishabh Jain

Introduction

At Locale.ai, we work with a number of last-mile and hyperlocal and mobility companies. For most of these companies, geospatial analysis is critical and typically, they have internal dashboards built on a BI platform or in-house using open source tools.

One of the reasons they use our product is to highlight what areas to focus on and how to contextualize their strategies to those areas. A caveat here is that these areas are not our traditional defined areas in a city or zip-codes. In this post, we will deep dive into why using traditional area definitions is not a good idea to carry out geospatial analysis.

Maps don’t always tell the truth!

Based on intuitive logic, companies either go with a zip-code boundary or some hand-drawn neighbourhood boundaries to map their most critical metrics like market potential, utilisation, average customer value, etc. These form an important part of decisions like what areas to expand into, shoot promotions in, or provision more supply.

Now, if you’re a business with little or no intra-city operations, the difference might not be significant to you. But if you provide services in the last mile or at a hyperlocal level, the differences in insights have a significant impact on the decisions that the business and city teams use.

Which brings me to the next question: Why is this difference significant?

Often what happens is the zip codes or arbitrarily defined neighbourhood boundaries that the nuances that the different areas depict tend to get dissolved.

In other words, a zip code that we treat as one big cell for analysis consists of many smaller cells without any similarity in demographics or economic potential.

This is illustrated by the fact that, if you live in Palo Alto, you are a part of the world’s foremost innovation hub and are paying median home prices of $1.18 million. However, just right across the train tracks, 18% percent of East Palo Alto residents live below the poverty line where the average yearly income per person is $18,385.

The characteristic behaviour of these two areas would be very different and while they would be present in the data that you collect, they often aren’t so easy to unearth.

In the next section, we would like to show you how easily the maps can lie and why different members in your team recommend completely different areas in a city to focus on based on the same set of metrics!

NYC City Manager’s Woes

Let’s consider that you are Uber’s city manager, and want to run contextual promotions and discounts in areas where you have high market potential or market share. For this exercise, we used the Uber Cab dataset available here and the NYC Yellow Taxi dataset available here. Now, we can simply define market-potential as

For our area definitions, we choose the NYC housing areas and NYC zip-code areas. Using these two area definitions, we calculate the market potential and here’s the plot:

Greener means more Market Potential for Uber and pinker means it is already doing well in that area. When we try to filter areas by M.P greater than 70% to identify the top areas to run promotions in, we see the following areas:

The areas we got are quite different!

Modifiable Areal Unit Problem

Hence, it is safe to conclude that the decision completely changes based on what set of boundaries we use for our analysis. This is a classical problem in geospatial data science known as the Modifiable Areal Unit Problem (MAUP).

Because of the MAUP problem, our decision becomes reliant on the shape and size of the area instead of the actual characteristics of the users within it.

The ideal area should have the ideal shape and size. Let’s consider finding that ideal shape. We could divide the geographic plane into squares of the same size, or maybe triangles, pentagons, or something else! We at Locale use hexagons instead of any other shape and you can get a glimpse of why here:

Spatial Modelling Tidbits: Honeycomb or Fishnets?

Let’s use hexes to plot the MP for NYC. Uber has a well-suited library that converts lat, longs to hexes of a given size. You can find out more about it here.

From the visualization, we can see the distribution of Market Potential across the city in a much uniform way. We can filter these hexagons by market potential to get the best area to run promotions in.

Another way to reduce more bias would be to not bind locations to areas initially which leads to our next section.

Enter, Geo-spatial Clustering!

The idea is to let data decide what the significant areas are on which MP should ideally be computed. A simple density-based clustering algorithm like DBSCAN could be a good place to start! We have written about the other types of clustering in case you want to check that out:

Geospatial Clustering: Types and Use Cases

We cluster all locations based on proximity to each other, hence finding dense clusters. Then, we compute the convex hull of these areas to get area boundaries. Now, we have areas generated from the data itself, suitable for computing MP in a reduced human-bias way. Again, we filter by areas where M.P is more than 70% and get these places:

It’s worth noting that a simple density-based approach can work here because of the nature and definition of the problem.

Since we consider only locations, a density-based spatial clustering extracts the underlying areas which are more closely knit in terms of the user behaviour.

For this decision to be actually reliable for a business use case, instead of using just one metric, we take a set of metrics that largely affect the user behaviour in one area. For example, office-goers in an area vs university students might show completely different travel patterns.

Now, as highlighted here, using the automated learning techniques for similarity and clustering analyses that we have built at Locale.ai, our algorithms work hard to find what areas behave similarly based on the metrics that you care about (growth potential, unit economics, power users) and show you what areas to focus on for each unit of your business.

This enables you to save or export these areas profiles and keep reusing them for different kinds of analysis and then track them to maximize your revenue, demand and profitability in each of those areas rather than using arbitrarily defined boundaries.

The complete experiment along with the code is available here. Feel free to experiment with some other dataset!

If you’ve reached this far, here is a sneak peek into why this forms the base of our entire platform and what all techniques we have developed on top of this:

Similarity Analysis and Feature Importance

Our geospatial models not only find clusters of areas having a unique characteristic, but also tell us why the area is unique. Hence, while identifying clusters of areas based on a combination of metrics, it also pinpoints the factors that have the most significant impact on these metrics.

Two different areas don’t necessarily have to be close in order to behave similarly. You can probably use one as a test area to observe and apply the same strategies across cities.

Real-time Monitoring with Anomaly Detection

It doesn’t make sense is not quite enough to just know that SLAs are not being met only in Bangalore or SFO. Knowing where orders are getting delayed or cancelled, or whether an abnormally high delay in an area is caused by a sudden supply drop because of rain can be very valuable.

Adding the context of location along with anomalies can make the insights very actionable for us and makes decision-making very simple.

At Locale, we are building an analytics and visualization product to help city and business teams get precise, real-time insights about how their operations perform without any compromises and dependencies. then get in touch for a demo here or get in touch with me on LinkedIn or Twitter.

Read Similar:

Spatial Autocorrelation: Close Objects Affecting Other Close Objects

Originally published at https://blog.locale.ai on May 15, 2020.

Key Takeaway

If you are a company with salespeople on the ground selling products, services, insurance policies, and loans, you can use location analytics to improve the productivity of your workforce and give better customer experience. This blog explains how.

Introduction

While working with different kinds of workforce companies who have thousands of salespeople on the ground, we have seen that despite collecting large amounts of data, only ~5% of that data actually gets used. Because of a dearth of the right tools for location analysis, a significant amount of decisions that are taken about operations and movement ends up being gut-driven.

As a result, the productivity of salespeople goes for a toss and we end up ignoring more revenue that we can make by improving utilization as well as taking more precise and data-driven decision.

“Location” is an inherent characteristic of anything that is happening in the physical world. Moreover, location intelligence is so much more than tracking on the map or solving the traveling salesmen problem! In fact, any decision involving the physical world is about location because everything is happening somewhere.

Therefore, it becomes very critical to incorporate location as a parameter and make it a first-class citizen in your decisions and strategies.

Location-Based Decisions for Workforce Use-Cases

In this part, we will cover different kinds of location analyses and the insights that you need to grow sales and utilization.

1- Monitoring Movement of Reps

Monitoring movement of salespeople on the ground for performance, ETAs, halts, bottlenecks is the most basic but the most critical use case for most workforce companies.

City and business teams also monitor KPIs such as idle sales reps, busy sales reps, sales made in real-time across locations to know what’s going on with their business and check for anomalies.

Often, companies also go back in time and do historical analysis of the movement patterns ( ie ‘breadcrumb’ trail) to analyze metrics such as distance traveled, time taken, places visited, delays etc to settle claims and detect inefficiencies.

You can also create cohorts of salespeople in case you aim to monitor the movement for a certain group and stay on top of their journey. For example, evaluating the lowest-performing salespeople.

2- Sales Mapping of Areas

Just analyzing the movement of reps is not adequate. We also need to analyze how different areas perform in different categories and with the time of the day and day of the week. But why? To get answers like:

Is there a specific location, time or day when we see a boost in the sales number? Which category is most sold in the affluent areas in the city?

Because that will help us close more sales by doubling down on areas that we see more opportunity and need to penetrate further, or seizing new opportunities by expanding in the right areas or sometimes just ignoring the areas that haven’t proven to be good for our business.

One very interesting application of this analysis we have seen companies do is debugging whether the sales numbers are low because of a particular area or a group of sales reps and how that’s been changing historically.

3- Offices, POIs or Any Static Locations

Now comes the third part of the puzzle — Analyzing the performance of your offices, POIs and locations where reps go and sell to. Using these insights to set up more targeted and personalized sales strategies for your customers.

Which offices are most frequently visited & never visited? Which offices have gotten us to the most revenue day-on-day? Where do sales reps spend a lot of time but don’t see enough conversions?

Some very interesting use cases that we have seen companies adopt are:

• Flagging all the instances and offices where sales reps spend less than an hour or more than 10 hours at a location.
• Analyzing the distance variation of the actual location of the rep versus the office location.

4- Fraud Patterns

This is a very common use case for all our customers. Most of them go through some kind of fraud/cases of misconduct/malicious activity/incorrect behavior from their workforce. That could range from providing false information of clients, giving incorrect scans, hacking biometric system and the list goes on!

Most of these events have hotspots, with location and time patterns. Companies use this to classify areas as “red zones” and as soon as they detect any kind of suspicious activity in those areas, they take precautionary steps.

Why should you use Locale.ai for workforce use cases?

Locale is a location analytics platform, which means we convert your raw lat-long data across all databases and formats into meaningful insights so that decision-makers can make very precise, data-driven decisions about their ground operations.

If on one hand, we give you the right metrics and insights to help you make the right decisions, we also make the process of working with large amounts of data very seamless and reduce the time to insight. We bring all your location data in one place to make these analyses available in a matter of a few clicks!

Monitoring Movement of Reps

With Locale, you can monitor the movement of your reps in real-time as well as get a historical timeline of their movement patterns. However, what makes this monitoring extremely powerful is the anomaly detection models we have built-in in the system. This means, we study your data historically and alert you with a severity score in case a metric behaves abnormally in a particular area.

Sales Mapping of Areas

Locale helps you identify your hotspots in terms of sales and visit frequency. But, what’s interesting is we just don’t give these insights at an area level because we believe that they are too big. We go down deeper into different areas to help you discover the nuances inside them, using a system of hexagonal grids.

Offices, POIs or Any Static Locations

Locale is amazing at giving you a bird’s eye view of all your offices or the places your sales reps visit. We use a mixture of size and color attributes to help you in a glance figure out which of those locations do you need to focus on or change your strategy. In other words, focus on the places with the maximum visits and lowest revenue generated.

Frauds

Acknowledging that this data might be sensitive, we have roles and permissions built-in along with showing the right hierarchy at each role. In other words, a city manager wouldn’t be able to get any such insights excluding his city.

Actions and Decisions

Apart from giving you the right insights, we also help you take actions and decisions on top through our workflows module. You can create a step-by-step flowchart that sends triggers to your reps on ground as well as get alerts in case of anomalies.

At Locale, we are creating examples of companies who are improving their unit economics, cost per delivery, utilization by doing geospatial analytics. Our product helps you analyze and improve metrics at a city level upto an order level. If you would like a demo, check our website out or get in touch with me on LinkedIn or Twitter.

Similar Reads:

• How to Improve User Acquisition & Conversion using Location Analytics
• Carto vs Kepler vs Locale: Which product to use for geospatial analytics?

Originally published at https://blog.locale.ai on May 5, 2020.

Carto vs Kepler.gl: Which tool to choose for location analytics?

A comparison of the geospatial tools for different use cases

A brief introduction to the tools

Carto and Kepler.gl are the tools that companies use in their analyses to make decisions about ground operations. In this piece, we compare them on factors ranging from technology to target users.

Kepler.gl

Kepler.gl is a web-based platform to visualize large-scale location data. It was created and open-sourced by the visualization team at Uber with the mission to create industry-grade open source frameworks to supercharge big data.

Carto

Carto is an open-source location intelligence platform built on PostGIS and PostgreSQL. CARTO (formerly called CartoDB) is a Software as a Service (SaaS) cloud computing platform that provides GIS, web mapping, and spatial data science tools.

Locale.ai

At Locale.ai, we are building an “operational” analytics platform using location data for supply and operations teams in on-demand companies. Similar to how web analytics tools (Google Analytics, Mixpanel, Clevertap) give analytics for web products using clickstream data, Locale helps to analyze and optimize your on-ground operations using geospatial data.

Comparision

This image shows the comparison between the three tools in a nutshell on different features or parameters. This section dives deeper into all of the parameters.

1- Analysis & Visualizations

Kepler.gl

Kepler is one of the best geospatial visualization tools for exploratory data analysis (EDA). The Uber team has done thorough and detailed research on the kind of visualization features relevant to mobility companies.

One of its biggest drawbacks is that any kind of processing that needs to be done on the data needs to be done outside. Kepler.gl is, unfortunately, a desktop tool that takes data only in the form of CSV, JSON, and geoJSON files.

These characteristics make it very painful when you are dealing with large amounts of data and need to keep downloading CSVs to plot onto the tool

Carto

Carto’s visualization and analysis capabilities are much more horizontal casting a wide net on the use cases they tackle as a company which includes different kinds of filters, widgets. They also have several built-in analyses (pre-built functions to help you manipulate data) inside the product.

The downside over here is that all these analyses can only be done on one data set at a time. Hence, the pre-processing out here also needs to happen outside the system, especially in cases of more complicated data sets.

Locale

At Locale, we have tried to include the best of both worlds. We have taken the inspiration from Kepler for visualizations and added analyses onto the product — not as functions but instead as use cases. We also ingest all your data across different databases, formats, and systems, get it onto a single place and model it so that it becomes super easy to be able to carry out these analyses.

2- Target Personas

Kepler.gl

Kepler.gl is targeting mostly business users, who essentially don’t know how to write code or SQL because of its sheer simplicity. However, we have seen a vast number of data scientists across Google and Airbnb adopting it for visualizations.

Carto

Carto is positioned as a location intelligence platform with an aptitude for data analysis and visualization that does not require previous GIS or development experience. Their UX tailored to the needs of modern web developers and data scientists. Their visualizations can be used for business users to make decisions.

Locale

Our target users at Locale are also business users as well — supply and operations teams, product teams, strategy teams and marketing teams inside companies. We have found that they are the ones who are in maximum pain and most of the time end up using excel sheets. They still depend on an analyst for BI reports or developers for live dashboards.

3- Target Industries

Kepler.gl

As mentioned before, since Kepler has been open-sourced by Uber, quite a lot of its features are much more relevant to mobility companies. It’s also used heavily by academicians and journalists since they don’t deal with large amounts of data live streaming.

Carto

Since Carto acts more like a platform, they end up working with a wide variety of clients ranging from governments to finance to healthcare to logistics.

Locale

We think of our market as every company with moving supply and/or demand. This includes on-demand delivery, micro-mobility, logistics, supply chain, as well as workforce companies.

4- Use Cases

Kepler.gl

Kepler.gl is mainly used for geospatial visualizations. Some examples of maps that have been built on Kepler are:

• California Earthquakes
• New York Cab Rides
• San Franciso Elevation Contours
• New York City Population
• San Franciso Street Tree Map

Carto

The use cases that Carto dabbles with are:

• Site Planning: Driving site selection and investment decisions
• Logistics Optimization: Optimizing supply chain design
• Territory Optimization: Aligning sales and service territories
• Geomarketing: Targeting users based on where they are & how they move
• Mobility Planning: Better infrastructure decisions & reducing traffic

Locale

The use cases that we at Locale tackle with are:

• Lifecycle Analysis: Analysis of the user, rider or order journey to reduce drop-offs.
• Supply-Demand Analysis: To analyze mismatch in demand (orders) and supply (riders) and reduce idle time.
• Trip analysis: To analyze trips and movement to increase utilization.
• Single Trip Analysis: To create profiles of a single user, bike or trip based on movement patterns.
• Station Location Analysis: To analyze the performance of static (or fixed) entities.

5- Technology

Kepler.gl

There are four major suits available in Kepler.gl — Deck, Luma, React map and React vis — to make beautiful data-driven maps. It is built with deck.gl and utilizes WebGL (A JavaScript API) to render large data faster and efficiently.

Carto

Carto’s web app is called Builder where users can manage data, run user side analysis and design custom maps. The CARTO Engine, which is a set of APIs and developer libraries is built for creating custom maps and data visualization interfaces. The tool uses JavaScript extensively in the front end web application, backend rails based APIs, and for client libraries.

Locale

Locale.ai uses a wide range of powerful open-source tools to handle large scale datasets in front-end and backend. The frontend is powered by Uber’s Deck.gl for high-performance visualizations, Nebula.gl for additional editing capabilities and Mapbox-GL for rendering maps.

Unlike other platforms, Locale provides the ability to ingest a large amount of data both in realtime and on-demand to analyze and gain insights on the fly. The backend is powered by python, PostgreSQL and PostGIS for powerful data processing and geospatial operations.

Building it Internally

While working with some of the leading on-demand and micro-mobility companies, what we observed that they end up hacking around these open-source tools like Kepler itself or QGIS.

Sometimes developers also build their own internal tools, but most of the time they are not well suited for all different audiences inside the company and since the tools are not built in a scalable way, maintaining these suck up a lot of their bandwidth often!

A lot of times there is even a repetition of effort and the wheel keeps getting re-invented over and over again. As Jeff Lawson from Twilio said —

“It is easier than ever to build software but harder than ever to operate it”.

Why Choose Locale?

So, if you are a company that decides to build this internally, it would have to be built like a platform itself, (much like how Uber has done it) and with the following characteristics:

• Simple and intuitive user interface to carry out analyses, especially for business users
• Scalable geospatial visualizations with actionability
• ETL robust enough to handle streaming data as well as historical analysis to go back in time

This would require setting up a team of at least 6–7 (consisting of the front end and data engineers, geospatial analysts as well as data scientists). On top of that, the added pain of waiting for at least 6 months to build the platform and kickstart the analyses.

If you want to delve further, check our website out or get in touch with me on LinkedIn or Twitter.

Originally posted here.

Similar Reads

• Kepler & QGIS: A brief analysis of the open-source geospatial tools
• What does Supply-Demand Gaps Mean for On-Demand & Last-Mile Delivery?

Carto vs Kepler: Which tool to use for geospatial analytics? was originally published in TDS Archive on Medium, where people are continuing the conversation by highlighting and responding to this story.

For app-based delivery + logistics + mobility companies where “location” is critical.

An app-based delivery company delivers whatever users order through their app right at the user’s location, anytime. On-demand companies such as food delivery companies, supply chain companies like e-commerce companies, hyperlocal delivery companies, and mobility companies all come under this category.

With all these companies, there is one thing in common: they have operations and moving assets on ground. Hence, location becomes very important as a parameter to include in strategies and decisions.

But, how can we use location analytics to increase user acquisition, conversion, and retention? Believe it or not, geographic patterns about these metrics can tell us a lot about our business and users. For example:

Not everyone who installs your app uses it or opens your app orders. In that case, is there a location where the density of churn is very high?

In this piece, we are going to discuss how we use location analytics to understand how we can improve our user acquisition, conversion, and retention.

Case 1: User Acquisition

Acquiring users in locations where there is already demand will help us reduce our CAC (customer acquisition cost). Hence, in choosing the next location where you want to expand, a good question to ask is:

Where are the locations that I already see a lot of latent demand in terms of app installs, searches, orders placed etc.?

We can use this insight to decide which area we need to establish partnerships with stores or restaurants, or where to open up a new vehicle or charging station, or which location to become serviceable in.

Similarly, if you are a mobility company with a significant percentage of power users, the next question that is crawling in your mind is:

How do these power users move and where do come from and go to?

Understanding these characteristics can determine what kind of locations and user personas we need to double down on. For example, are these users office goers or students?

Case 2: User Conversion

At the core of conversion, is the fact that there is churn. Today, when people do churn analysis, they only look at the persona and the step of the funnel. Every user that didn’t convert is revenue lost in front of us.

However, analyzing where the churn is happening is critical because that helps us identify where we need to improve operations, provision supply, or do offline marketing.

Between when users open the apps to when he finally makes the payment for the order, there are a large number of steps that occur in between in the app.

To book a ride:
Enter destination → searching the nearest bike → selecting the bike → starting the trip.

To order food:
Select cuisine → Select restaurant → Select the dish → Checkout → Make payment

For example, a grocery company that we are working with realized that people were churning out from the ordering process once they saw the SLAs and they realize they can get better SLAs somewhere else! When we plotted the churn data, we noticed some high-density clusters in cities, and the team started focusing on provisioning more delivery partners in those areas.

Case 3: User Retention

Once you convert a user, how do you ensure repeatability and retention? After all, we all know that retention is one of the most important metrics for a company as it ensures consistent revenue. But, in a world where users can switch across multiple competitors at the tap of a button and with their demands of the highest quality service, it’s harder and harder to ensure retention.

Different companies have different strategies for retention. Some companies do up-selling: Getting users to order the same catalog at a higher frequency while some companies do cross-sell: Getting users to order across different categories and catalog.

Location can help in retaining users as well be pushing very targeted promotions based on the user’s location and behavior.

For example, let’s go back to our mobility company example. Suppose we figure out that our most valuable users are students who take our vehicles from hostels to colleges. We can run a campaign subsidizing these routes!

Out of home (OOH) advertising is also a very popular marketing strategy to nurture and retain your users and the success of this strategy depends on the right messaging and the location.

How do you get started?

Locale is a location analytics platform, which means we convert your raw lat-long data across all databases and formats into meaningful insights so that decision-makers can make very precise, data-driven decisions about their ground operations.

Web analytics tools already help you improve these metrics, using clickstream data. However, with companies that have moving assets on the ground, not looking at things geospatially can be extremely detrimental! Let’s dive deeper into how you use can increase user acquisition, conversion, and retention using location analytics.

Acquisition

Demand Mapping lets you overlay your search data and install data that you can use to analyze the spatial and time-wise trends for different areas. Growth Heads can use these insights to identify which areas are untapped and for the business for different categories.

Conversion

Churn Analysis helps you analyze where different events happen geospatially and where are people churning out the most at a very granular level. Whether you need to open a vehicle station hub to provide more stations or call the manager of the restaurant with the highest prep time or do some offline events — the decision is yours.

Retention

Workflows module helps you take actions in cases when certain metrics and thresholds are met. Companies use this to send very targeted geo-promotions to their users or get alerts in case their KPIs observe anomalies.

At Locale, we are creating examples of companies who are improving their unit economics, cost per delivery, utilization by doing geospatial analytics. If you are a growth manager looking to improve user acquisition, retention, and conversion, then get in touch for a demo here or get in touch with me on LinkedIn or Twitter.

Originally posted here.

Similar Reads:

• Location Analytics for delivery & mobility companies with ground operations
• Location Analytics for Your Supply Chain Using Locale.ai during Covid-19

How to Improve User Acquisition & Conversion using Location Analytics was originally published in TDS Archive on Medium, where people are continuing the conversation by highlighting and responding to this story.