<?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[Stories by Fenix Engineering on Medium]]></title>
        <description><![CDATA[Stories by Fenix Engineering on Medium]]></description>
        <link>https://medium.com/@fenixintl_Tech?source=rss-d411887a988a------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*bIu3XiRASo3S7srcvcARqw.jpeg</url>
            <title>Stories by Fenix Engineering on Medium</title>
            <link>https://medium.com/@fenixintl_Tech?source=rss-d411887a988a------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Wed, 18 Nov 2026 20:06:44 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@fenixintl_Tech/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[The interplay of experimentation and ML to aid in repayment of micro-loans in Sub-Saharan Africa]]></title>
            <link>https://medium.com/@fenixintl_Tech/the-interplay-of-experimentation-and-ml-to-aid-in-repayment-of-micro-loans-in-sub-saharan-africa-8db65e59cfb0?source=rss-d411887a988a------2</link>
            <guid isPermaLink="false">https://medium.com/p/8db65e59cfb0</guid>
            <category><![CDATA[iot]]></category>
            <category><![CDATA[finance]]></category>
            <category><![CDATA[africa]]></category>
            <category><![CDATA[software-development]]></category>
            <dc:creator><![CDATA[Fenix Engineering]]></dc:creator>
            <pubDate>Thu, 12 Sep 2019 14:08:36 GMT</pubDate>
            <atom:updated>2019-09-16T07:26:59.098Z</atom:updated>
            <content:encoded><![CDATA[<p>Imagine that through a twist of fate, rather than living the life that brought you to reading this today, you were born in rural Uganda to subsistence farmers. You didn’t have much access to school, and now as an adult you also earn your living through farming cassava and maize. On average, you earn about 60 USD per month, but it’s mostly split across two harvest seasons a year. With this cash, you have to budget for all your household needs: food, charcoal, clothing, school fees, healthcare, phone charging, and oil for a kerosene lamp to work at night.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Tm9v6AT3VqJKGTKb7iy1OQ.png" /></figure><p>The smoke from the lamp causes coughing, and the light isn’t bright enough to see well, so your kids aren’t able to study past sunset. The risk of fire is also high, only last week your neighbour tipped his lantern over, almost burning down his hut. An efficient solar panel and power system would provide cleaner, safer, and brighter light at night, as well as the ability to charge a basic cell phone to keep in touch with family. However, even a small reliable kit costs around 100 USD, and you have no documented financial history to apply for a loan.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*H-MZN8TexKZEai5dUXdruQ.png" /></figure><p>This is the situation for around <a href="https://www.worldbank.org/en/topic/energy/publication/sear">600 million</a> (!) people in Sub-Saharan Africa. Easy-to-use digital financial technology is allowing companies like Fenix International to offer solar home systems on loan; our customers can pay off their kits with small payments (as low as $0.14 per day) over the course of 1 to 3 years. Even with affordable financing, our lower income, rural customers can face significant challenges to keep up with their payments. Seasonal income from farming, seasonal expenses like school fees, and shocks like medical bills can make cash flow and payments quite irregular. The customer may experience challenges making payments due to poor availability of mobile money agents or if the mobile money network is down. And if there is an issue with the product itself, such as a faulty solar panel or — as often happens in Uganda — if a rat has chewed through the wires, the customer will resume payment only once the issue is diagnosed and resolved.</p><p>All of this uncertainty and complexity makes <a href="https://www.cgap.org/blog/growth-vs-sustainability-credit-risk-paygo-solar">data an essential part</a> of helping Fenix International customers <a href="https://medium.com/f4life/machine-learning-in-paygo-what-you-need-to-know-before-you-jump-in-54ec905b03f">stay on track with their repayment</a> — through analytics, predictive modeling, and A/B testing around interventions. Data from multiple different sources, including customer demographics, regional information, IoT data from the solar kit itself, as well as the customer’s own past repayment patterns, are used to understand when and how to intervene when one of our customers is falling behind on their loan, and to work with them throughout their repayment process.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*0d2sVafhCy0pg7h30DwPZg.png" /></figure><p>One of the ways Fenix interacts with our customers is through our call centers, which service dozens of local languages and can be very resource-constrained during peak hours and as we grow quickly in a market. We use predictive modeling to bring efficiencies to our customer experience by allowing us to identify customers who may need a call from us, and to prioritize calls to customers who are both likely to answer and who are more likely to make a repayment or have an issue resolved after receiving a call from our customer service team.</p><p>Fenix uses data and analytics to identify and solve specific pain points in the customer journey, as well. We found that customers who are late to their first digital payment (after their initial deposit) are more likely to default on their loan. As a result, we created a random forest model to predict who would be late to their first payment and are now testing how much a preemptive call from our call center increases initial payments in that group. These data will also serve to train a second model to predict the customers who are likely to respond well to a call, allowing us to use our exceptional call centre representatives effectively.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Nx0VAU-6DAfESscnByQmgg.jpeg" /></figure><p>We are constantly iterating and experimenting with different initiatives and behavioral interventions setting up control groups and measuring effects and ROI. We go into the field and interact with kit-owners to better inform our feature engineering and selection and to evaluate the customer journey. Our IoT pipeline analyses millions of pieces of information sent daily from our devices to understand product usage and if this usage predicts future payment behavior. At ODSC, I’ll talk more about the mix of experimentation and machine learning that we use to increase financial inclusion and adoption of sustainable energy sources, as well as some of the issues that we’ve faced and hard lessons that we’ve learned working in this <a href="https://www.cgap.org/blog/expanding-horizons-pay-you-go-solar">really exciting and unique</a> space.</p><p><strong><em>Written by: Brianna Schuyler. She leads the data team at </em></strong><a href="https://www.fenixintl.com/"><strong><em>Fenix International</em></strong></a><strong><em>. After completing her PhD in Neuroscience in 2012, she served as a Peace Corps volunteer in Uganda. She is thrilled to be able to apply her experience working with big data to contribute to the development of sustainable energy and address issues faced by people living in rural, Sub-Saharan Africa.</em></strong></p><p><em>Article </em><a href="https://opendatascience.com/the-interplay-of-experimentation-and-ml-to-aid-in-repayment-of-micro-loans-in-sub-saharan-africa/"><em>originally posted</em></a><em> on ODSC by the author, who will be speaking there this fall</em></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=8db65e59cfb0" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Day in the Life of…Ali Ziwa!]]></title>
            <link>https://medium.com/@fenixintl_Tech/day-in-the-life-of-ali-ziwa-68a545507a20?source=rss-d411887a988a------2</link>
            <guid isPermaLink="false">https://medium.com/p/68a545507a20</guid>
            <category><![CDATA[agile]]></category>
            <category><![CDATA[software-engineering]]></category>
            <dc:creator><![CDATA[Fenix Engineering]]></dc:creator>
            <pubDate>Tue, 13 Aug 2019 07:53:39 GMT</pubDate>
            <atom:updated>2019-08-13T07:53:39.286Z</atom:updated>
            <content:encoded><![CDATA[<p>Like all other professions, software engineers too have normal days, good days, and HARD days.</p><p>A really good day is where I am closing ticket after ticket, Product Manager &amp; QA are happy and the team is in sync. 🎊</p><p>Most normal days begin with completing any pending work from the previous day. This is usually because the first thing I see when I open your laptop is the IDE staring at me with the last line of code I wrote from the previous day. I then read some tech news to be up to date with current trends, have stand-up and then lunch time comes around. I jump right back to coding or pick a new ticket which could be a new feature, bug or an enhancement.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/416/1*_WdF8j3ZOaXLSuJzgLlpzA.png" /></figure><p>Side Note: Any new ticket goes through our development workflow. A ticket is created, scoped and prioritized by the Product Manager and discussed with the engineering team when planning the week’s work (called a sprint). An engineer picks up the highest priority ticket, writes code to solve it, writes automated tests to test the functionality and sends it to 2 other engineers to review the implementation. Once code review passes, it is then assigned to the QA engineer who verifies it and it’s impact to the entire Fenix software. If all is good, the ticket is assigned to the Product Manager who validates it and marks it as DONE!</p><p>That next ticket might be your nightmare and this brings us to the hard days. Hard days are usually long days that have me sleeping at 3am and up at the crack of dawn. They start subtly; I pick a ticket, plan the execution and jump into coding. But things start falling apart, dots are not connecting anymore, headphones get on, usually referred to as “zoning in” (Note: It’s always polite not to disturb an engineer with headphones on, kindly slack😊). It gets to 4:30pm, then 6pm, 9pm and nothing seems to be working. Stack overflow becomes my best friend, I take a walk, play some basketball, still nothing. I get home, take a nap, still nothing, then at around 3am, I might dream of a solution, jump right out of bed and, well, turns out the dream was a hoax. This can get worse with the Zeigarnik effect (states that people remember uncompleted tasks all the time…like a lingering garlic breath.) I think about it on the toilet, while having a coffee, getting a rolex from Maureen’s canteen, literally all the time.</p><blockquote>It’s always polite not to disturb an engineer with headphones on…</blockquote><p>I share it during our daily stand up meetings but the frustration starts setting in after 2 days and this is when I usually decide to “pair program” (Two Engineers sitting together with one laptop trying to solve an issue). We work on the issue as a team and “try” to close that ticket such tickets are the ones where the QA always gets something you missed and throws it back at you for not passing the requirements😩. But once all cycles finally get to pass, this hard day that stretched into 7+ days, is celebrated with PTO 😅.</p><p><strong><em>Written by: Ali Ziwa also known by his underground coder name, Sensei Lee. In his free time, Ali likes to flex his table tennis muscles and practice Swahili.</em></strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=68a545507a20" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Proudly Ugandan; WPD 2019 in Kampala]]></title>
            <link>https://medium.com/@fenixintl_Tech/proudly-ugandan-wpd-2019-in-kampala-8fab9b9f189c?source=rss-d411887a988a------2</link>
            <guid isPermaLink="false">https://medium.com/p/8fab9b9f189c</guid>
            <category><![CDATA[world-product-day]]></category>
            <category><![CDATA[africa]]></category>
            <category><![CDATA[product-tank]]></category>
            <category><![CDATA[kampala]]></category>
            <dc:creator><![CDATA[Fenix Engineering]]></dc:creator>
            <pubDate>Tue, 28 May 2019 13:15:13 GMT</pubDate>
            <atom:updated>2019-05-28T13:30:13.853Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/800/1*jLlis_4bOcX8L35tPULryA.png" /><figcaption>World Product Day Kampala</figcaption></figure><blockquote>KULIKA WORLD PRODUCT DAY!</blockquote><p>The best translation we could agree on for “Happy World Product Day” in Luganda, one of 41 local languages spoken in the country and the mother tongue of the Kingdom of Buganda where Kampala sits. A relatively young ProductTank, we begin humbly on June 20th 2018 with 12 eager participants (6 from the host company). Since then we have increased the number and diversity of members as well as meet frequency with WPD representing our most successful gathering yet. Around 50 product owners, software engineers and entrepreneurs hopped on a boda (motorcycle taxi) to the HQ of <a href="https://safeboda.com/ug/">SafeBoda</a>, the market leader of safe transportation in Kampala. In their edgy industrial style open office space we enjoyed some <a href="http://nilebreweries.com/wp-content/uploads/2016/11/Nile.jpg">Nile Special</a> (local beer) and celebrated uniquely Ugandan products with our theme:</p><blockquote>“PROUDLY UGANDAN”</blockquote><p>After a brief introduction to ProductTank &amp; World Product Day we moved onto the presentations from 9 people developing products in Uganda, for Uganda. Each presenter had 10 minutes to answer these four questions:</p><p><em>1.Who are you?<br>2.What product did you help build?<br>3.What problem are you solving?<br>4.What is unique about building products in Uganda?</em></p><p>We heard about a variety of products during the showcase, addressing fundamental life issues regarding access to clean energy and clean water from <a href="http://fenixintl.com/">Fenix International</a> and <a href="https://spouts.org/">Spouts</a>. We saw the power of data collection and insights across the public and private sector with <a href="https://www.numida.co/">Numida Technologies</a> and <a href="http://pollicy.org/">Pollicy</a>, who provide sophisticated technical solutions to a wide customer base with limited tech capabilities. Staying on the tech theme, <a href="https://safeboda.com/">SafeBoda</a> discussed their passenger application and <a href="https://www.dignited.com/">Dignited</a> talked about their work and responsibility in the world of technology reporting. Greta Thunberg would be pleased to hear that the environment was not forgotten with <a href="http://www.reformafrica.org/">Reform Africa</a> and <a href="http://www.kimulifashionability.org/">Kimuli Fashions</a> showing us how we can help solve Uganda’s waste management problems while looking fly! Last but not least we had Manana from <a href="http://milege.org/">Milege Foundation</a> walk us through the entire value chain they’re building to allow musicians to be their most authentic selves; encouraging traditional music forms, mentorship, promotion and festivals!</p><p>Despite the motley crew of product owners we all agreed on some fundamentals. Building products in Uganda is great because we can be so close to our customers, every company here has the ability to visit their customers on a regular basis and they’re keen to be involved in product design and testing. We also recognised that Uganda (like many other African countries) has a very unique set of challenges, which allows <a href="https://www.ted.com/talks/toby_shapshak_you_don_t_need_an_app_for_that">true innovation</a> (such as <a href="https://www.ifc.org/wps/wcm/connect/news_ext_content/ifc_external_corporate_site/news+and+events/news/impact-stories/mobile-money-africa">mobile money</a>) to happen. It’s not all a bed of roses however, as we all face limitations with the cost of manufacturing and policies that can stifle innovation.</p><p>Keep your eye on <a href="https://www.facebook.com/producttankkla/">ProductTank Kampala</a> as we continue to solve our unique problems with nimble customer centric solutions.</p><p>Amy Elizabeth Robinson<br>Director of Software Product / ProductTank KLA Organiser</p><p>Fenix International<br><a href="http://arobinson@fenixintl.com/">arobinson[at]fenixintl.com</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=8fab9b9f189c" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[How does Fenix approach data analysis?]]></title>
            <link>https://medium.com/@fenixintl_Tech/how-does-fenix-approach-data-analysis-1bc89ec2f2ce?source=rss-d411887a988a------2</link>
            <guid isPermaLink="false">https://medium.com/p/1bc89ec2f2ce</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[fenix]]></category>
            <category><![CDATA[big-data]]></category>
            <dc:creator><![CDATA[Fenix Engineering]]></dc:creator>
            <pubDate>Wed, 18 Jul 2018 11:41:39 GMT</pubDate>
            <atom:updated>2018-07-20T07:34:15.684Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ZvgWeq4871xqP2Ek-k5qDw.jpeg" /><figcaption>Photo by <a href="http://freeforcommercialuse.net from Pexels">Markus Spiske</a></figcaption></figure><p>When I first joined Fenix Intl’s data team, I was blown away by how data-literate the Fenix business was. It wasn’t just the skill of their existing data team members, but also the way in which the different teams across the business self-serviced data and made their own data driven decisions.</p><p>Having come from a large organisation where data driven decisions still seemed to be heaped on to a handful of members of a data analytics team, it was refreshing to see teams such as finance, marketing and product development taking it upon themselves to build their own reporting and carry out their own analysis.</p><p>This is why Fenix is not exaggerating when it calls itself a data driven business. Everything from the design of its latest generation products, to the way it staffs its call centres has been arrived at through the analysis of data.</p><p>With so much demand on data analysis throughout the business, it’s no surprise that Fenix’s small but growing data team has had an important role to play, which is why I would like to describe Fenix’s approach to data analysis, from my point of view as a new member of their data team.</p><p>There’s a lot of emphasis put on “data” by the industrial press, often with the tagline that “data is everything” for a business. While this claim certainly has merit, I feel that the value of data isn’t actually realised until it is analysed, insights have been uncovered, and it has been used to tell <strong>a story</strong>.</p><p>I believe that this represents a key part of the Fenix data team’s approach to exploring data. The data, and the analysis, are both a means to an end. They’re not the prize at the end of the rainbow, they’re the fuel and the engine that help us get there.</p><p>This is why we always try to start our data analysis projects by understanding the business problem, or the overarching objective of our stakeholders. After all, they’ve got a goal they need to hit, and putting ourselves in their shoes will do a lot to help guide the analysis.</p><p>Another key part of our approach that probably seems obvious; we familiarise ourselves with the data, and understand its limitations. Is an increase in a household’s expenditure being caused by a new product launch, or is it really because fuel prices have gone up and people have no choice but to spend more?</p><p>At the same time, we try to remind ourselves to avoid analysis paralysis. It’s easy to sink two hours into working out whether users responding to an interaction were doing it via a smartphone or feature phone, but ultimately if a stakeholder just needs to know how many positive responses came from the interaction, they won’t even look at the insight.</p><p>We also try to anticipate our audience’s questions. This comes back to putting ourselves in our stakeholder’s shoes.</p><p>What would we want to know if we were running their business unit?</p><p>What would our immediate priorities be?</p><p>The data and the analytics become less important. It’s the “so what?” that counts.</p><p>What’s the insight that will help them make that next decision?</p><p>Finally, we try to keep it simple.</p><p>This is easier said than done.</p><p>How can we keep insights simple for someone after spending weeks building and training a machine learning model which looks at hundreds of variables just so that we can forecast out sales?</p><p>This is the part of data analysis a lot of people find most difficult. Any analyst will want to showcase the complicated, scientific and rigorous process that they undertook to analyse the data given to them. So much so that the audience is likely to get lost in the detail and feel like they never got the insight that they were promised.</p><p>It’s important to find a balance between communicating the key insight to a stakeholder, whilst at the same time assuring them that we’ve explored every avenue or possible pitfall in the data.</p><p>We won’t claim that this is always easy. For most people (including myself) it’s likely going to be a trial and error process where you learn from doing.</p><p>I hope this insight into Fenix Data’s approach to data analysis has been helpful to other practitioners. Next time you’re embarking on some data analysis, just remind yourself of why you’re doing it, and who you’re doing it for.</p><p><strong><em>Written by: Alex Roussel, who is on the data team</em></strong> <strong><em>at Fenix. Alex likes to salvage old bikes and restore them in his free time</em></strong></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1bc89ec2f2ce" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[<fenix>Hello World</fenix>]]></title>
            <link>https://medium.com/@fenixintl_Tech/fenix-hello-world-fenix-b66ebe6e1ec?source=rss-d411887a988a------2</link>
            <guid isPermaLink="false">https://medium.com/p/b66ebe6e1ec</guid>
            <category><![CDATA[kampala]]></category>
            <category><![CDATA[fenix]]></category>
            <category><![CDATA[uganda]]></category>
            <category><![CDATA[solar]]></category>
            <category><![CDATA[renewable-energy]]></category>
            <dc:creator><![CDATA[Fenix Engineering]]></dc:creator>
            <pubDate>Tue, 29 May 2018 07:21:04 GMT</pubDate>
            <atom:updated>2018-05-29T07:59:39.082Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/910/1*BZTotc96D8tU8IXo9jLaVw.jpeg" /><figcaption>Fenix Tech Team goofing it up on Entebbe Beach</figcaption></figure><p>We are very excited to be part of the Medium community to talk about the even more exciting things we are up to in our Kampala HQ.</p><p>Our team is made up of people from dynamic backgrounds and experiences and we thought of this awesome medium (😉) to open up the Fenix world to the rest of the tech community out there.</p><p>This blog will enable us to show you what we are up to in the tech department and our cool workspace. We talk about the tech we are working on, events we are attending, experiences and even our field trips! Feel free to follow us here to stay up to date.</p><p>Follow us on <a href="https://twitter.com/fenixintl_tech">Twitter</a> for even more exciting updates.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*1gK8jiPTGEeptG_0L_UKng.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b66ebe6e1ec" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>