Predictive modelling will advance financial inclusion as the rural business case improves: a case study in Uganda

Christian Ruckteschler
30 Jan 2018

By Christian Ruckteschler

  1. Introduction

A key aspect of responsible finance is inclusion: ensuring that the financial system works not only for the wealthy and urban but for all members of society. Yet achieving financial inclusion in the poorest and most remote rural areas remains a difficult feat. The lack of economic viability keeps banks and other financial institutions out of remote areas, and even mobile money agents are currently far and between. This may be about to change. With a quickly rising mobile phone penetration rate, rural areas are moving into the focus of business interest. Mobile Money operators are increasingly focusing their growth strategy on an expansion into the more remote areas. A case study in Uganda suggests that MNOs see themselves in a competition to service new areas and hence new customers. In this post, we argue that they are right: our analysis shows that an increasing share of potential high-value customers is located in rural areas. Hence, financial inclusion goals and business incentives are becoming more aligned. We expect access to mobile money to reach many more remote rural areas in the near future.

This analysis is a result of research by IFC’s Applied Research and Learning Program under the Partnership for Financial Inclusion and further elaborates on a case study presented in the Handbook on Data Analytics and Digital Financial Services. Through a long-term research engagement with Airtel Uganda and in collaboration with the Bill & Melinda Gates Foundation, the team analysed two six-month periods of anonymized Call Detail Records and Airtel Money transaction records for the entire Airtel Uganda customer database (Nov 2014 – Apr 2015 and Oct 2016 – Mar 2017). In this post, we present findings from a predictive model we built using machine learning methods to identify high-potential mobile money customers. Using the results of the model, we find that the geographic distribution of high-potential customers is much more spread out in 2016 than it was in 2014.

  1. A key user group to focus on

To better understand mobile money users, we first segmented the customer database and followed customers over time. A helpful tool for this analysis were diagrams that visualize the flow of customers between different segments over time, known as Sankey diagrams. This revealed the existence of a small group of key customers which set themselves apart along several dimensions: they transact more frequently, generate more revenue than any other segment, and are more stable over time. Consequently, this small group of “Highly Active Users” accounts for a large share of the service’s revenue. In addition, their active usage makes the network more useful and attractive to other customers. MNOs would thus be well-advised to focus on growing this segment, and to work on identifying non-users with a high probability of falling into this segment if activated.

  1. Identifying High Potentials

To identify high-potential non-users, we built a machine learning model that predicts a GSM user’s Airtel Money customer segment. The first significant finding is that this was possible: using only call detail records, the model correctly predicted a user’s customer segment in 85% of cases. The model generates a prediction score between 0 and 1 for each GSM user, indicating the user’s probability of becoming Highly Active. Ordering GSM users with no mobile money activity according to this score provides a ranking of the most high-potential users to target. Comparing user activity two years down the line to the predictions of the model shows that it works remarkably well. Converting the highest ranked customers to mobile money users through targeted marketing could significantly grow the Highly Active segment, boosting revenue and overall business performance.

Linking such a prediction model to geographic information can inform business decisions and growth strategies by uncovering which geographic areas have the highest density of high-potential users. This is particularly important for MNOs as they look to expand into rural areas. One aspect of responsible finance is to serve clients reliably and sustainably. Taking a data-driven approach can help MNOs identify where this is feasible.

  1. Financial Inclusion: Business Interests and Development Goals Increasingly Aligned

To learn more about the urban-rural split of high potential GSM-only users, we plotted their density on a map of Uganda, using cell tower locations to approximate their whereabouts. For reasons of confidentiality, we use customer data from 2016 to illustrate here. Predictably, many high potentials are located in and around Kampala, the capital city. Yet less predictably, a significant share of them is located far from the capital and in more remote areas, as Figure 2 illustrates. This represents a marked change from two years prior (2014), and implies that Airtel should have a growing strategic interest to increase their mobile money presence in remote areas. Such an expansion would substantially increase financial inclusion.

Figure 2 – Density of high-potential non-users (2016 data)


We find that a marked shift has taken place in the attractiveness for mobile money operators in Uganda to serve rural and remote areas. While the business case previously led MNOs to focus on urban areas, more and more high potential users are now located in rural areas. They can be found by using the data analytics methods discussed here and in our published handbook. MNO’s expansion strategies suggest that those in charge are aware of this trend. We suspect that Uganda is not unique in this regard but that the attractivity of rural areas to mobile money operators is increasing in many countries across Sub-Saharan Africa together with mobile phone penetration. This is a good message for responsible finance: we can expect business interest to drive financial inclusion of remote areas in the next years. Preliminary indicators suggest that the Highly Active segment is moving down market, too: not only are High Potentials more geographically spread, they are poorer than before, too.

This case study also demonstrates the significant potential for big data analytics to inform expansion strategy and enable effective targeted marketing campaigns. Predictive models can identify not only High Potentials as demonstrate here but other user categories as well. For instance, we have built similarly accurate churn prediction models to target customers even before they leave the service. MNOs in Sub-Saharan Africa are only beginning to tap into this potential.


Adapted from a case study presented in the Data Analytics and Digital Financial Services Handbook (June, 2017), this post was authored by Christian RuckteschlerIFC-Mastercard Foundation Partnership for Financial Inclusion, for the Responsible Finance Forum Blog January2018. We thank Nicolais Guevara and the team at Cignifi Inc. for their tremendous work without which this analysis would not have been possible.

Fraud in Mobile Financial Services: Protecting Consumers, Providers, and the System

09 Sep 2017

This Brief highlights how fraud is impacting mobile money providers, agents, and consumers, as well as efforts to reduce risks and vulnerabilities to fraud in mobile money and related services. While it is not possible to remove fraud entirely from any service—mobile money included—the examples addressed here show that fraud is a major issue in several key markets for consumers and agents, and that there are simple steps providers can take to reduce their vulnerability to common fraud types.

These steps include improving internal controls, building agent capacity to protect themselves and their customers, and revisiting procedures such as account access and SIM swaps, where necessary, to prevent common fraud schemes. With the introduction of new products and delivery channels, the types of fraud will continue to evolve, which means that monitoring mechanisms, such as compliance checks and customer feedback channels, will continue to be key elements to effective fraud and risk mitigation.

Building a Secure and Inclusive Global Financial Ecosystem

08 Sep 2017

The 2017 Brookings Financial and Digital Inclusion Project (FDIP) report evaluates access to and usage of affordable financial services by underserved people across 26 geographically, politically, and economically diverse countries. The report assesses these countries’ financial inclusion ecosystems based on four dimensions of financial inclusion: country commitment, mobile capacity, regulatory environment, and adoption of selected traditional and digital financial services.  The report further examines key developments in the global financial inclusion landscape, highlights selected financial inclusion initiatives within the 26 FDIP countries over the previous year, and provides targeted recommendations aimed at advancing financial inclusion.

Going rural with digital financial services

Karima Wardak
05 May 2015

When a family member first told Mary that she could use her mobile phone to store her money, she felt that she had finally found a safe place to keep the earnings from her vegetable sales.  Mary soon experienced, however, that the journey to register and manage an account to be less simple.

At a four-day event in Uganda, UNCDF brought together 150 digital financial service providers from 20 countries in Asia and Africa to improve their understanding of the challenges faced by low-income entrepreneurs like Mary and find  solutions for them.

An event for learning and sharing experiences

MG_4880Understanding the “user journey” was at the core of the learning event organized for grantees and partners from two UNCDF programmes, MicroLead and Mobile Money for the Poor.  Through meeting and talking with agents and clients directly, the participants, who were mostly providers of digital financial services (DFS), were able to identify ways to improve their services in rural areas by taking a more customer-centric approach. They also got an improved sense of how their ’cashless’ services can better meet the needs of farmers and small entrepreneurs in rural areas.  Participants also discussed savings group linkages, rural agent management, smallholder farmer initiatives and service design for poor rural households.

The participants came from countries ranging from the Lao People’s Democratic Republic, Myanmar and Nepal to neighbouring Ethiopia, Malawi and Senegal. They represented the entire DFS ecosystem: financial service providers (Equity Bank, FidelityBank, Laxmi, NBS Bank and Opportunity International, to name a few), mobile network operators (Airtel, MTN, Ncell, Tigo, etc.), central bank and ministry of finance representatives, as well as other non-banking providers and funders.

The field visit or “user journey” was an eye opener for digital financial service providers. It changed the way the participants approach the development of new DFS products, partnerships, and delivery channels.

Lessons learned and quick solutions from the user journey include:

Problem 1: Costly and time-consuming registration and know-your-customer (KYC) procedures: Not only does Mary need a passport photo but she also needs a copy of a valid ID, which is no small challenge in rural areas where photocopy machines are scarce, copies costly and finding a photographer can be next to impossible. When she does have the opportunity to get a picture taken by a professional photographer, chances are good that it will take several weeks if not a couple of months before the photographer returns with the precious prints. In such a situation, participants heard that clients like Mary are willing to sacrifice a family picture—even a wedding photo!

Participants at an Airtel store during the field visit in Jinja, Uganda . Photo Credit:  Malaika Media UgandaPotential solution 1: Some participants visited agents that offer to take the picture themselves through a device provided by the DFS provider. This solution seemed to be an obvious option to many participants to consider for their own countries and as a good investment in their attempt to improve the experience of DFS users.

Problem 2: Lack of literacy: Once Mary has collected all required documentation, she returns to her preferred agent with her phone and some cash for her first deposit. The agent then proceeds with registration, which in the best case scenario takes a couple of minutes but can take up to three weeks if the network fails to connect properly and activate the account. Since Mary cannot read or write, the agent completes the documentation paper work and holds Mary’s phone to show her how to manage the SMS messages. Mary painfully signs and accepts whatever fee the agent requests from her as she cannot read the poster that displays the official tariffs.

Potential solutions 2: Participants explored the potential that smartphones can offer and how short videos can be delivered on simple phones. This approach effectively replaces the written word, and is a practise used successfully by Freedom from Hunger in West Africa.

Problem 3: Long distances and lack of liquidity: Mary’s journey does not become easier after she is registered. To deposit cash, she plans a 15-kilometre trip to the nearest agent on the same day she sells her vegetables at the market. The journey comes at a cost, as waiting in a long line for her preferred agent takes time away from her business.On occasions when she needs cash, Mary knows that her preferred agent might not have the cash and be able to provide her with what she needs.

Potential solutions 3: What are the best options to keep agents afloat? Could providers recruit and train super agents capable of answering the urgent need for cash? Or would it help to map an agent network to ensure that clients can find an agent within five kilometres of their residence? Besides these ideas, another solution that emerged was turning every client into an “agent” as distance would then no longer be an issue. Each client could turn to one of their community members and manage transactions to either cash out or cash in money.

These are just three examples of challenges faced by low-income people in rural areas and possible solutions to improve the registration and usage of DFS. The realities faced by agents and clients revealed pain points that the DFS providers had never considered before.  Participants took the lessons learned from the training, especially the client and agent visits, home with them to adapt them into tailor-made solutions for their digital financial services clients.  One participant, Webster Chidze Mbekeani from TNM Malawi, said he would try his best to help people like Mary “by understanding her needs better rather than trying to just prescribe a solution”. Francis Matseketsa from Airtel Malawi went a step further, declaring: “I will roll out an engagement plan that ensures that the client is equipped with adequate information on the product and she knows where to go or how to contact us when she needs help. I want Mary to be delighted with our service.”