<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[voyanceHQ - Medium]]></title>
        <description><![CDATA[Data science made easy - Medium]]></description>
        <link>https://medium.com/voyancehq?source=rss----12c5ba1e8a21---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>voyanceHQ - Medium</title>
            <link>https://medium.com/voyancehq?source=rss----12c5ba1e8a21---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 07:35:53 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/voyancehq" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Designing Voyance Vision on Voyance Cloud]]></title>
            <link>https://medium.com/voyancehq/designing-voyance-vision-on-voyance-cloud-2eb370eed4ef?source=rss----12c5ba1e8a21---4</link>
            <guid isPermaLink="false">https://medium.com/p/2eb370eed4ef</guid>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[ocr]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[kyc]]></category>
            <category><![CDATA[computer-vision]]></category>
            <dc:creator><![CDATA[Sebiomo Aanuoluwapo]]></dc:creator>
            <pubDate>Mon, 16 Aug 2021 11:10:04 GMT</pubDate>
            <atom:updated>2021-08-16T11:10:04.458Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*GWT2GAd9PPlp_gDEAx_kjA.gif" /></figure><p>Every day, businesses, both big and small, have to analyse tons of documents supplied by their customers during the compliance processes to ensure that these documents are legal, correct and have not been tampered with.</p><p>This can be a tedious task and takes a lot of time. The question we had to answer was:</p><p><strong>How can we simplify this process, so that businesses can focus on more important tasks like improving product features and delivering excellent customer care?</strong></p><blockquote>The answer was Voyance Vision.</blockquote><blockquote>A computer vision solution that provides an automated, fast, accurate platform that is able to handle processing limitations such as low image quality or poorly scanned documents.</blockquote><p>Voyance Vision is a part of Voyance Cloud that allows businesses to create and train models or use existing models created by our Data Engineers to extract texts from documents such as invoices, receipts, passports, drivers licenses, or other forms of documents.</p><p>Voyance Vision uses OCR technology to make this possible. OCR stands for Optical Character Recognition. It converts texts or information extracted to machine-readable data. These data can be edited or stored for further processing. Voyance Vision uses Artificial Intelligence and Machine Learning to make this possible.</p><p>Although OCR has a vast use case, the use case for this application would be to verify and approve legal documents and automate data extractions from these documents and store them for future use. This step is crucial in compliance processes.</p><h3>About the Project</h3><p>Voyance Vision is a cloud-based solution that helps businesses solve computer vision problems related to document and image analysis.</p><p>Voyance Vision v1 allows users to extract texts from images. Future updates will include PDF documents.</p><p>Product Manager: Jennifer Okafor</p><p>Product Designer: Sebiomo Anuoluwapo</p><p>Research Engineer: Odunayo Ogundepo</p><p>Frontend Engineers: Oluwanifemi Adeyemi, Isaac Bello, Victor Akinyemi</p><p>Backend Engineers: Temi Babs, Patrick Ojunde, Vicky Foukou</p><h3>A Practical Problem Vision Solves.</h3><p>The FinTech space is a fast-growing niche in Nigeria with each company having thousands of users. According to <a href="https://techcabal.com/2021/03/18/kuda-bank-series-a-25-million-dollars/">TechCabal</a>, Kuda bank has about 650,000 customers, Paystack has about 60,000 customers according to <a href="https://techcrunch.com/2020/10/15/stripe-acquires-nigerias-paystack-for-200m-to-expand-into-the-african-continent/">TechCrunch</a>, CowryWise has over 220,000 customers (<a href="https://techcrunch.com/2021/01/28/owrywise-raises-3m-pre-series-a-to-scale-its-wealth-management-platform/#:~:text=About%20that%2C%20Cowrywise%20has%20more%20than%20220%2C000%20users.">TechCrunch</a>), these are only a fraction of the companies in Nigeria.</p><p>As a part of the compliance process which ensures the authenticity of each customer and the overall integrity of the platform, customers need to submit any government-issued ID such as Driver’s license, Nation ID Card (NIN), Passport, Voter’s Card and or CAC Documents for businesses.</p><p>It can be a daunting task to manually go through the tons of documents submitted each day. These manual processes of extracting the needed data from these documents can be expensive, time-consuming, and error-prone.</p><h3>The Vision Solution.</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*M34ez00J8DWJDI83zKeCbA.png" /></figure><p>Voyance Vision is a solution that helps reduce cost and the time spent processing these documents without compromising on the accuracy of data extraction.</p><p>Voyance Vision gives companies the ability to train their models or use our pre-built models that have been trained by our Data Engineers.</p><h3>Our Process</h3><p>We have simplified the process from start to finish to enable our users to get started right off the bat.</p><p>First-time users are given a free 14-day trial period and a specific amount of API calls, which allows them to use our services without any commitments.</p><p>After the trial period, users are required to make payments to continue using Voyance Vision.</p><p>Users can easily get started using our prebuilt models which do not require training as our Data Engineers have taken time to train models that can be used immediately.</p><p>Files can be added locally, with the plan for future versions to support Google Drive and Amazon S3 Bucket.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*lGfHB1qwm4diKQEJ" /></figure><p>Once the data have been extracted, they can be stored for future use in third party databases that we support. These are MySQL, MariaDB, Amazon Redshift and Postgres.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*ghj4Og0WVCvsx5ua" /></figure><h3>The Technologies We Used.</h3><p>Our Engineers used:</p><ul><li>Tensorflow, an open-source library for machine learning, mostly used for deep learning, was created by the Google Brain team.</li><li>Pytorch, also an open-source library for machine learning, is commonly used for Computer Vision and Natural Language Processing.</li><li>OpenCV and</li><li>Kubernetes, a software orchestration tool.</li></ul><h3>Challenges we Faced</h3><p>The major challenge was identifying the specific solution we were going to offer at launch.</p><p><em>Because computer vision is so robust, you can do a thousand things with infrastructure like Vision. So my work was to cut out many parts to create what our “right-now” clients need.</em></p><p><em>Also, what we are building, an AI infrastructure is more complex than your everyday tech product.</em></p><p><em>Personally, I had to learn fast and have a clear picture of the product, to help the team with understanding it too. I am still doing the learning aspect because people are always coming to me with questions, and I should have the answers.</em></p><p><strong>- Jennifer Okafor, Product Manager.</strong></p><p><em>The disparity in the understanding of the problem was also a challenge.</em></p><p><em>This was tackled by sharing concise product documentation across the team, and having regular sessions with the product team, to avoid assumptions.</em></p><p><em>Formalization of the engineering tasks, going from product description to a precise engineering breakdown. Architectural decisions had to be made, options had to be weighed carefully to optimize the code for efficiency and scalability.</em></p><p><strong>- Temi Babalola, Senior Software Engineer.</strong></p><p><em>Working on this project, for me, was a learning experience.</em></p><p><em>Before this moment, I did not have any background knowledge in OCR technology, Computer vision, Machine learning and Artificial Intelligence.</em></p><p><em>I had to study and do research to develop an intuitive design that solves the problem. Working with the team on this project was amazing.</em></p><p><strong>- Sebiomo Aanuoluwapo, Product Designer.</strong></p><h3>The Results We Got.</h3><p><em>With Voyance Vision, our customers started securely extracting data from thousands of IDs, easily transferring the needed data to the right departments.</em></p><p><em>For one of our clients, a task that would have taken them 8 months was completed in days. All at a significantly lower cost!</em></p><p><em>With the infrastructure Voyance provided, this company got:</em></p><p><em>An automated document verification process.</em></p><p><em>A connection hub to extract, transform and load data from different sources for easy data management.</em></p><p><em>Intelligent business intelligence and behavioural analysis.</em></p><p><strong>- Folasade Daini, Content Marketing.</strong></p><p>Voyance Vision takes out the slow, manual, and error-prone system and replaces it with AI-powered infrastructure that cuts out expensive intermediaries and manual work. It also provides access to a connection hub for easy data management and a machine learning-based prediction tool.</p><p>All the tools you need are available to you in a single platform, helping you save thousands of dollars you’d have spent on multiple vendors.</p><blockquote>Let nothing stop you from getting these results for yourself. Start saving your business time and money now. <a href="https://voyancehq.com/">Begin your free 14-day trial now.</a></blockquote><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=2eb370eed4ef" width="1" height="1" alt=""><hr><p><a href="https://medium.com/voyancehq/designing-voyance-vision-on-voyance-cloud-2eb370eed4ef">Designing Voyance Vision on Voyance Cloud</a> was originally published in <a href="https://medium.com/voyancehq">voyanceHQ</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[My internship experience at Voyance]]></title>
            <link>https://medium.com/voyancehq/my-internship-experience-at-voyance-542d632f1663?source=rss----12c5ba1e8a21---4</link>
            <guid isPermaLink="false">https://medium.com/p/542d632f1663</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[internships]]></category>
            <category><![CDATA[blessing-mikairu]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[voyance]]></category>
            <dc:creator><![CDATA[Blessing Mikairu]]></dc:creator>
            <pubDate>Thu, 30 Jul 2020 04:10:07 GMT</pubDate>
            <atom:updated>2020-07-30T06:05:50.001Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*n0rWsqVesQhKT2nFHn8jOw.png" /><figcaption>Data science at Voyance</figcaption></figure><p>In October 2019, I successfully completed my Udacity Data Science nanodegree facilitated by a scholarship I got from the African App Launchpad initiative. For my capstone, I built two projects using SQL and Python, respectively. A few months down the line, I was stuck in tutorial hell. In addition, I barely used any of these at my day job as I mostly worked out of Google Sheets for my data needs. I could feel the knowledge slipping out of my grasp.</p><p>I thought about how best to get real-world experience. Voyance had launched in December 2019, and Abdul would regularly post Medium articles focused on the product. So, I thought, where best to learn data science than at a data science company? I reached out to Abdul, asking for the opportunity to intern at Voyance. After some back and forth with Abdul and Ebot, I started my internship on the 6th of April.</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fgiphy.com%2Fembed%2F3ohs4fvauGyov7Wp3y%2Ftwitter%2Fiframe&amp;display_name=Giphy&amp;url=https%3A%2F%2Fgiphy.com%2Fgifs%2Fnba-player-court-3ohs4fvauGyov7Wp3y&amp;image=https%3A%2F%2Fmedia1.giphy.com%2Fmedia%2F3ohs4fvauGyov7Wp3y%2F200.gif&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=giphy" width="435" height="245" frameborder="0" scrolling="no"><a href="https://medium.com/media/283c151a09772852fb4fffcdba2bfa17/href">https://medium.com/media/283c151a09772852fb4fffcdba2bfa17/href</a></iframe><h3><strong>Structure</strong></h3><p>The internship required a roughly 20-hour commitment every week. As I am an insomniac, most days I worked during the early hours. Ebot designed a curriculum that covered supervised and unsupervised learning. The premise was simple: learn a particular machine learning algorithm and build a simple project with it. Rinse and repeat.</p><h3><strong>Weird Lessons</strong></h3><p>This experience featured one of the steepest learning curves I have experienced. This is saying a lot as I am a self-taught career generalist who studied Law and has always worked in tech. It was not the couple of lines of code required to run each of the algorithms that was the problem. It was the maths.</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fgiphy.com%2Fembed%2FAPqEbxBsVlkWSuFpth%2Ftwitter%2Fiframe&amp;display_name=Giphy&amp;url=https%3A%2F%2Fgiphy.com%2Fgifs%2Fmath-thinking-APqEbxBsVlkWSuFpth&amp;image=https%3A%2F%2Fmedia1.giphy.com%2Fmedia%2FAPqEbxBsVlkWSuFpth%2Fgiphy-downsized-large.gif&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=giphy" width="435" height="481" frameborder="0" scrolling="no"><a href="https://medium.com/media/bd5d6756cb3d3351c17c1a93c4388d57/href">https://medium.com/media/bd5d6756cb3d3351c17c1a93c4388d57/href</a></iframe><p>At the beginning, I struggled. I was frustrated with my pace. Frustrated at how complex articles tagged “Machine Learning for Dummies” were. Ebot was super supportive and after a while, I learned to be not so hard on myself.</p><p>An important lesson I also learnt was that it is possible to go too far down a rabbit hole. I realised, and this is rather counter-intuitive, that if I spent over 4 hours trying to figure out why a single line of code was not working (believe me, I did that on multiple occasions), the actual solution was not in adding successive lines of code to fix the first problem. Instead, the solution was in deleting that line, closing my Jupyter notebook, and coming back to it after I have slept. I would often find that all I had to do was to write that line again and the problem would be something ridiculously simple (e.g. switching from \ to /).</p><h3><strong>What did I build?</strong></h3><p>I built projects using various machine learning algorithms including logistic regression, random forest, and k-means clustering. I built them mostly using Python and data science libraries including sklearn, matplotlib, dumpy, pandas, graphviz, hyperopt, and pickle.</p><p>One of the projects I worked on was classifying mall customers based on their income and spending level. On this project, I learnt how to solve an unsupervised learning problem using clustering, specifically, k-means. For this, I used numpy, pandas, matplotlib and sklearn.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/935/1*oaX04O88vmu6kgSvfCI1fw.png" /><figcaption>Visualisation of elbow method to find the optimal number of clusters</figcaption></figure><p>The most important lesson learnt building this project was tying findings to business goals. Ultimately, predictions do not live in a vacuum. You are running the model for a reason. In the instant case, a business owner would set his marketing targets on people who earned high and spent high (green).</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*YqEp__XRdUWHnLIvBA7LWA.png" /></figure><p>The logistic regression project was on the classic titanic dataset. Essentially, predictions of survival were made based on various parameters such as age, sex, passenger class etc. It was interesting for various reasons: it was my first machine learning model; it required me to walk though a data pipeline from loading the data, to cleaning it up, training the model, optimising it, and then saving it. It was also my first experience using hyperopt for hyperparameter optimisation which as I have learnt outperforms other methods of model tuning. I may have invented colourful invectives in the process.</p><h3><strong>What is next?</strong></h3><p>I am incredibly grateful to Abdul and Ebot for the experience. I had no idea how everything would pan out when I sent that Facebook message. As it turned out, I could not have gotten a more supportive mentor than Ebot. While I am not quitting my day job as a PM soon, I will continue to learn and build stuff.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=542d632f1663" width="1" height="1" alt=""><hr><p><a href="https://medium.com/voyancehq/my-internship-experience-at-voyance-542d632f1663">My internship experience at Voyance</a> was originally published in <a href="https://medium.com/voyancehq">voyanceHQ</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Enable intelligent decisions with Voyance Omniscient.]]></title>
            <link>https://medium.com/voyancehq/enable-intelligent-decisions-with-voyance-omniscient-fbc3bc66da42?source=rss----12c5ba1e8a21---4</link>
            <guid isPermaLink="false">https://medium.com/p/fbc3bc66da42</guid>
            <category><![CDATA[business-process]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[african-startup]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Abdul]]></dc:creator>
            <pubDate>Thu, 07 May 2020 16:08:12 GMT</pubDate>
            <atom:updated>2020-05-07T16:25:20.932Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*5ThykzVwN_n_y3ltArOsVQ.png" /></figure><p>Data is the biggest asset to any company. As a growing business, you can’t afford to overlook the benefits of your data. Today, data is collected by your business in every possible way.</p><p>If you do not have the army of data scientists like Google, Facebook, Amazon, or Apple, how can you setup machine learning for your business? What are the opportunities right now?</p><h3>How can machine learning work for your business ?</h3><ul><li>Predictive analysis to predict outcomes</li><li>Making your product smarter</li></ul><h3>Predict outcomes</h3><p><strong>Predictive analysis</strong> uses your historical data to <strong>predict</strong> future events. With Voyance Omniscient, we can help you use your historical data to to spin up a machine learning model that captures important trends.</p><p>That <strong>predictive</strong> model is then used on your current data to <strong>predict</strong> what will happen next, or to suggest actions to take for optimal <strong>outcomes</strong>.</p><h4><strong>Example</strong></h4><p>A fin-tech company with historical data on fraudulent transactions can use that to build a machine learning model to predict fraud on new transactions.</p><h3>Make your product smarter</h3><p>As mentioned above, some companies can integrate machine learning into their infrastructure to gain and learn from in-depth consumer behavior insights but another option for companies is to use machine learning to power feature additions that allow them to grow quicker than their competitors.</p><h4>Example</h4><p>An e-commerce company can make use of their historical data to build an intelligent product recommendation system with Voyance Omniscient.</p><h3>Summary</h3><p>The potential impact of machine learning on business is enormous. Machine learning allows businesses like yours to anticipate and preemptively satisfy customer needs or reduce the amount of errors and manual work.</p><p>With Voyance, you don’t need an army of data scientists to implement machine learning for your business. We empower companies with our products combined with our in-house data scientist.</p><h3>Voyance Omniscient</h3><p>Omniscient is part of Voyance’s product suite that enables a quick and fast way for companies to spin up advanced machine learning models.</p><h3>How can you get started?</h3><p>We’re always excited to help companies get started with machine learning, most especially in Africa.</p><p>Visit <a href="https://voyancehq.com/">https://voyancehq.com</a> to book a free consultation time with our senior data scientist to understand your use case.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fbc3bc66da42" width="1" height="1" alt=""><hr><p><a href="https://medium.com/voyancehq/enable-intelligent-decisions-with-voyance-omniscient-fbc3bc66da42">Enable intelligent decisions with Voyance Omniscient.</a> was originally published in <a href="https://medium.com/voyancehq">voyanceHQ</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Is your data Machine Learning ready?]]></title>
            <link>https://medium.com/voyancehq/is-your-data-machine-learning-ready-ef2ec63fb1d9?source=rss----12c5ba1e8a21---4</link>
            <guid isPermaLink="false">https://medium.com/p/ef2ec63fb1d9</guid>
            <dc:creator><![CDATA[Abdul]]></dc:creator>
            <pubDate>Thu, 05 Mar 2020 14:08:54 GMT</pubDate>
            <atom:updated>2020-03-05T14:29:48.995Z</atom:updated>
            <content:encoded><![CDATA[<p>Automating data ingestion, cleaning and preparation with Voyance data science platform</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*HMtICIJg71YDFmvhG8OB3w.jpeg" /></figure><p>More than 80% of a data scientist’s time is spent on preparing data manually. While this is a good sign, considering that as good data goes into building the predictive model, the accurate gets the output.</p><p>But, data scientists should ideally be spending more of their time interacting with data, running advanced analytics, training and evaluating the right model, and deploying to production. Today, only 20% of the time goes into the major chunk of that process.</p><p>In order to overcome time constraints, companies need to reduce the time taken on cleansing and enriching the data by leveraging solutions for data engineering and preparation.</p><p>Most machine learning platform out there today focus 90% of their platform on helping businesses train and deploy model meanwhile without a good data, the deployed model is just as bad as not deploying it at all.</p><h3>Garbage in, Garbage out</h3><p>If you are new to data science, you need to understand that “garbage in, garbage out” applies to machine learning in data science.</p><p>The accuracy of your machine learning model is directly related to the cleanliness of the data it trained on.</p><h3>Let me give you an example:</h3><p>The image below contains historical data retrieved from a well established e-commerce business and we tried using it to train a machine learning model to see what the accuracy will be.</p><blockquote>Scope of work is to build a machine learning prediction model that will enable the e-commerce company to categorise a transaction as fraudulent or safe.</blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*1fuu3bSOoFF-0GoIhOB_yQ.png" /><figcaption>Voyance data science platform</figcaption></figure><h4>Below is the result of the training:</h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6vB1jrfYldeKl4O9NN6OkQ.png" /></figure><p>Here we can see that everything about this model is just bad. The accuracy, the Top importance, Coefs etc and that’s because the data we feed the algorithm with is unprepared and need some transformation, i.e the IP address needs to be transformed into countries and so much more.</p><blockquote>This is the part where data transformation comes in</blockquote><p>This is not a task you want to leave to highly paid, hard-to-find data scientist experts and that’s why we’re building this feature into our data science <a href="https://voyancehq.com/#omni-platform">https://voyancehq.com/#omni-platform</a> platform.</p><h3>Machine learning ready data</h3><p>If your company is looking to use data science to solve their problems or augment business process, you must allocate time and resources needed to clean data before building a machine learning model.</p><p>This is where Voyance can help with our transformation feature using our data science platform and in-house data analyst.</p><h3>Voyance is a full-service data science team for startups and organisations of any size.</h3><p>We take care of all your data needs at every step along your journey, from delivering insights and predictions using our OMNI platform and to setting up a scalable data infrastructure to empower you to answer any data question you might have.</p><p><em>Sign up for a free 30-minute chat with a senior data scientist here: </em><a href="https://calendly.com/voyance">https://calendly.com/voyance</a> or visit our website to learn more <a href="https://voyancehq.com/">https://voyancehq.com</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=ef2ec63fb1d9" width="1" height="1" alt=""><hr><p><a href="https://medium.com/voyancehq/is-your-data-machine-learning-ready-ef2ec63fb1d9">Is your data Machine Learning ready?</a> was originally published in <a href="https://medium.com/voyancehq">voyanceHQ</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Predicting customer churn at a bank with Voyance data science platform]]></title>
            <link>https://medium.com/voyancehq/predicting-customer-churn-at-a-bank-with-voyance-data-science-platform-16a9b8957d3c?source=rss----12c5ba1e8a21---4</link>
            <guid isPermaLink="false">https://medium.com/p/16a9b8957d3c</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[data-science]]></category>
            <dc:creator><![CDATA[Abdul]]></dc:creator>
            <pubDate>Fri, 28 Feb 2020 08:31:02 GMT</pubDate>
            <atom:updated>2020-02-28T10:00:39.787Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*-NNbzOlhwIw3uJb-2T9ytg.jpeg" /></figure><h3>Problem Statement</h3><p>Customer churn, also known as customer attrition, refers to the phenomenon whereby a customer leaves a company. For banks, acquiring new customers can cost five times more than satisfying and retaining existing customers.</p><h3>Why?</h3><p>Marketing costs to acquire new customers are high. Therefore, it is important to retain customers so that the initial investment is not wasted;</p><p>In this article, we’ll build a machine learning model using Voyance data science platform to predict how likely a customer is going to churn.</p><h3>Dataset</h3><p>Here’s a sample of our historical bank data</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*JQen3HMD8O8U8WRKjgnJYg.png" /></figure><h3>Using Voyance OMNI platform to build a model</h3><p>Now that we know what the problem is and we have the required data, we can go ahead and build a model to predict customer churn.</p><p>Here’s a video demonstrating how we used this data to build a model in less than 10mins:</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fwww.youtube.com%2Fembed%2FortIdIPcwW4%3Ffeature%3Doembed&amp;display_name=YouTube&amp;url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DortIdIPcwW4&amp;image=https%3A%2F%2Fi.ytimg.com%2Fvi%2FortIdIPcwW4%2Fhqdefault.jpg&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=youtube" width="854" height="480" frameborder="0" scrolling="no"><a href="https://medium.com/media/5f1cc3ed9f88cb2c8e81ca612aa2b83e/href">https://medium.com/media/5f1cc3ed9f88cb2c8e81ca612aa2b83e/href</a></iframe><h3>Voyance is a full-service data science team for startups and organisations of any size.</h3><p>We take care of all your data needs at every step along your journey, from delivering insights and predictions using our OMNI platform and to setting up a scalable data infrastructure to empower you to answer any data question you might have.</p><p><em>Sign up for a free 30-minute chat with a senior data scientist here: </em><a href="https://calendly.com/voyance">https://calendly.com/voyance</a> or visit our website to learn more <a href="https://voyancehq.com/">https://voyancehq.com</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=16a9b8957d3c" width="1" height="1" alt=""><hr><p><a href="https://medium.com/voyancehq/predicting-customer-churn-at-a-bank-with-voyance-data-science-platform-16a9b8957d3c">Predicting customer churn at a bank with Voyance data science platform</a> was originally published in <a href="https://medium.com/voyancehq">voyanceHQ</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Automate loan eligibility process with Voyance data science platform]]></title>
            <link>https://medium.com/voyancehq/automate-loan-eligibility-process-with-voyance-data-science-platform-51e12aa2eff2?source=rss----12c5ba1e8a21---4</link>
            <guid isPermaLink="false">https://medium.com/p/51e12aa2eff2</guid>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[data-scienc]]></category>
            <category><![CDATA[predictions]]></category>
            <dc:creator><![CDATA[Abdul]]></dc:creator>
            <pubDate>Sun, 23 Feb 2020 16:17:40 GMT</pubDate>
            <atom:updated>2020-05-10T12:36:45.843Z</atom:updated>
            <content:encoded><![CDATA[<h3>Automate loan eligibility process with Voyance machine learning platform</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*fsahGe4zh55RC1LVS2M_Bw.jpeg" /></figure><h3>Problem Statement</h3><p>Sama financing company deals in home loans. They have presence across all urban and rural areas in Nigeria.</p><p>Customer can apply for home loan online or at their office and after that, the company manually validates the customer eligibility for loan.</p><p>The company wants to automate the loan eligibility process (real time) based on the customer detail provided while filling the application form online or physically on a paper. These details are Gender, Marital Status, Education, Number of Dependents, Income, Loan Amount, Credit History and others.</p><p>To automate this process, they have given a problem to identify the customers that are eligible for loan amount so that they can specifically target these customers.</p><h3>Dataset</h3><p>The company provided the following historical dataset for building a predictive modeling to automate the loan eligibility</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*bSWI9oYgxHQd-MTo6SxM-g.png" /></figure><h3>Using Voyance OMNI platform to build a model</h3><p>Now that we know what the problem is and we have the required data, we can go ahead to build a model to automate new loan submission.</p><h3>Step 1</h3><p>Create a project and upload historical data on Voyance OMNI platform</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ozBEbz85-ENvkEw2DZwgwA.png" /></figure><h3>1.1</h3><p>Upload historical data</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*_DuPDhw_VKieTA2wX7Rf3A.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*W61uZxNr1SMCdjugHmvgEg.png" /></figure><h3>Step 2</h3><p>Select your model type and target variable</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3IW7WU67EzAfIVLALGml8w.png" /></figure><h4>What is a target variable?</h4><p>A target variable of a dataset is the feature of a dataset about which you want to gain a deeper understanding. In this case, its the <strong>loan_status</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DVg9UzICei51P9uURrRFCQ.png" /></figure><h3>2.1</h3><p>After selecting the model type and target variable, we can now name and create our model by clicking the “create model” button</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*wjoVSx111_lNDPo9UDnhnA.png" /></figure><p>Once that’s done, we can start training the model</p><h3>Step 3</h3><p>Once our machine learning model training is completed, we can now predict new customer loan request.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*t_ZwvKVkeReFN89tFRpKOA.png" /></figure><h3>3.1</h3><p>But first, we need to make the most performing algorithm (with best accuracy) active for our new prediction.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*83qeqlgJJLD_bdixjW5gLA.png" /></figure><h3>3.2</h3><p>After doing that, we can predict new customer data via web or API. But for this tutorial, we’re predicting via Web.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*gdIEtuMdpfOJGqMdD004Yw.png" /></figure><p>After selecting new customer data, we need to name the prediction and run our prediction.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Dhabtj2cARoDGFTQX3aYWA.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*WYoxxlIsHNSp73eAi7WYxA.png" /></figure><h3>Prediction</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Ww3nsflmYzVbVPmiEPJhtg.png" /></figure><blockquote>In this image, we can see the newly created columns: Prediction, prob_Y and proba_N</blockquote><h3>Definitions</h3><p>Y = Yes, Sama can loan this customer the requested loan amount</p><p>N = No, sama shouldn’t loan this customer the requested amount</p><p>As you’ve witnessed, we just created a loan eligibility machine learning model in less than 10mins.</p><h3>Setup something similar for your business</h3><p>To get started, visit <a href="https://app.voyancehq.com/request-access">https://app.voyancehq.com/request-access</a> or reach out to Voyance team at <a href="https://voyancehq.com/reach-out">https://voyancehq.com/reach-out</a> for personalised on-boarding for your business.</p><p>Our team will work with you to help gather data from disparate data sources, use our platform to clean and prepare it for predictions.</p><p>Looking forward to hearing from you :)</p><p><em>Voyants</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=51e12aa2eff2" width="1" height="1" alt=""><hr><p><a href="https://medium.com/voyancehq/automate-loan-eligibility-process-with-voyance-data-science-platform-51e12aa2eff2">Automate loan eligibility process with Voyance data science platform</a> was originally published in <a href="https://medium.com/voyancehq">voyanceHQ</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Making machine learning accessible to african businesses with Voyance]]></title>
            <link>https://medium.com/voyancehq/making-machine-learning-accessible-to-african-businesses-with-voyance-477c8256ad82?source=rss----12c5ba1e8a21---4</link>
            <guid isPermaLink="false">https://medium.com/p/477c8256ad82</guid>
            <category><![CDATA[africa]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[data-scientist]]></category>
            <dc:creator><![CDATA[Abdul]]></dc:creator>
            <pubDate>Tue, 17 Dec 2019 13:27:03 GMT</pubDate>
            <atom:updated>2020-03-29T11:31:49.606Z</atom:updated>
            <content:encoded><![CDATA[<h3><strong>Introducing Voyance: Helping startups transform data into future insights.</strong></h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mb6kem6wJa5NNRRxEe1bUQ.png" /><figcaption>Copyright Voyance</figcaption></figure><p>Increasingly, organisations in emerging markets like Africa are looking to machine learning to help them solve business problems and drive efficiency but implementing a machine learning project to drive impactful decisions requires a diverse team with expertise in several skill sets.</p><p>That&#39;s why demand for data scientists is soaring right now. Every company is looking for experts who can help them gain a data-edge over the competitors and make better predictions about the future.</p><p>Unfortunately, these professionals are expensive. In addition to that, it’s also very difficult to find quality data science experts because it’s such a new field where lack of validation still exists.</p><h3>But the good news is</h3><p>There’s a rise of data analyst in every organisations in West Africa, However, most find the aspect of AI (building and deploying Machine Learning algorithms) pretty daunting and <strong>still rooted deep within lines of intricate code and mathematics.</strong></p><p>These analysts need to learn the art of blending data from disparate sources, spreadsheets, databases (relational and NoSQL), unstructured data sources. They need to learn cleaning, summarizing and preprocessing the data before writing the code to find the best predictive model for their data.</p><p><em>Isn’t this overwhelming? Believe me, it is</em></p><p>Currently, there are about millions of data analysts in Nigeria alone that lack the necessary skill set and problem-solving ability.</p><p><strong>They’re really good users of BI tools but do not have a competitive edge when it comes to predictive analytics.</strong></p><p>Activating predictive analytics and unlocking the full potential of AI are complicated and time-consuming tasks. From data preparation to data modelling to deployment, an analyst needs technical skills and efficient decision-making ability which are not that simple to obtain.</p><h3>Introducing Voyance</h3><p>Our mission is to democratize machine learning for companies by providing a set of tools that frees them from relying on teams of data scientists.</p><p>Our flagship product is called OMNI which is coined from Omniscience which means the “the state of knowing everything”.</p><h3>Enter OMNI</h3><p>OMNI is automatic machine learning, which brings the power of world-class data scientists in the hands of everyone. lt builds models automatically using machine learning algorithms of every kind.</p><h3>OMNI can be used to build machine learning model to predict things like <strong>customer churn</strong>, <strong>transaction and infrastructure anomaly etc</strong>.</h3><h3>One of the most fascinating use cases we’ve seen with OMNI is <strong>automating reconciliation </strong>which is a major issue for organisations like banks.</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*vuDOowCbHMy5W3Q-kqFoBA.png" /><figcaption>OMNI Platform</figcaption></figure><h3>How does it work?</h3><p>We’ve literally made building a machine learning model as easy as using an instagram filter or setting up a wordpress page.</p><p>In three clicks, you’ll be performing predictions with your data!</p><h3>Step #1</h3><p>Upload your data from any source. We currently support CSV/TSV/ZIP file, any <a href="https://techterms.com/definition/rdbms">RDBMS</a> database like mysql, PostgreSQL, MongoDB and Amazon S3</p><h3>Step #2</h3><p>We automatically do the data cleaning and preparation part and display the dataset in a clean and beautiful table</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*e6RgMmT4D2zwOJmI-ygIUA.png" /></figure><h3>Step #3</h3><p>Select the appropriate machine learning method to train your model with i.e <strong>Predict</strong>, <strong>Classify</strong>, <strong>Flag</strong> etc</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Py4iqQZm3_uRHSn8i5Q3hQ.png" /></figure><p>Once that’s completed, OMNI prepares the data, automatically curates latest machine learning algorithms from and builds the best model.</p><p>You or your data analyst can then deploy these models with a single click to make predictions and business decisions via our beautiful web interface or API (<a href="https://docs.voyancehq.com/">OMNI documentation</a>) for technical users who would like to build a solution using the prediction API.</p><p>The main purpose of OMNI platform is to democratize AI within organizations so that ordinary individuals can:</p><ol><li>Use data to make predictions (build machine learning-powered use cases)</li><li>Bring different stakeholders together and access the value of the data science initiative as a whole</li></ol><p>Getting started on the AI journey is intimidating, but we at Voyance is here to ease that burden and provide a framework that allows you to learn as you go.</p><h3>Who is behind this?</h3><p>Voyance was started by ET, a senior machine learning engineer, who worked at Two Sigma as a senior data engineer (A $60B hedge fund that uses machine learning for its trading strategies) and co-founded by Abdul (AB), who previously worked as a product manager at Smartly AI (leading french artificial intelligence company) and Paystack.</p><h3>What’s happening next?</h3><ul><li>We’ll be adding more machine learning algorithms i.e neural network</li><li>Adding more data source i.e loggly, datahog, pagerduty etc</li><li>Releasing our runtime environment for ease of on-premise model deployment (#dataPrivacy)</li><li>Build dashboards to display predictions in a more beautiful way</li><li>Actionable recommendations based on predictions</li><li>Setting up a workshop soon in partnership with Techpoint, if you’re interested, kindly head over to the website and request for an invite.</li><li>and so much more in the buckets!</li></ul><h3>How do I get started?</h3><p>We are currently an invite only platform, working with companies and individuals with shared excitement about data science.</p><p>If you are excited and would like an invite to the platform, kindly head to <a href="https://voyancehq.com/">Voyance</a> and someone from the team or myself will reach out.</p><h3>Finally</h3><p>We envision a world where every company no matter how big or small, understands machine learning and uses it to improve their decision making.</p><p><em>If you have any comments or suggestions, reach out to us at </em><strong><em>hi@voyancehq.com</em></strong><em>. Thank you for reading and have a nice day</em></p><p><em>Join our community of AI enthusiasts:</em></p><p><em>Official Website: </em><a href="http://www.voyancehq.com/"><em>www.voyancehq.com</em></a></p><p><em>Twitter: </em><a href="http://twitter.com/@voyancehq"><em>@voyancehq</em></a></p><p><em>LinkedIn: </em><a href="https://linkedin.com/company/voyancehq"><em>@voyancehq</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=477c8256ad82" width="1" height="1" alt=""><hr><p><a href="https://medium.com/voyancehq/making-machine-learning-accessible-to-african-businesses-with-voyance-477c8256ad82">Making machine learning accessible to african businesses with Voyance</a> was originally published in <a href="https://medium.com/voyancehq">voyanceHQ</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>