SAVE Score - The alternative credit score for the unbanked

Savings and Credits Groups (SCGs) commonly known as VSLAs refers to a small group of people who save together and borrow from their pooled savings. They play a critical role in bringing financial services to rural areas of developing countries, where access to formal financial services is typically very limited. SCGs came as an intervention aimed at improving local financial intermediation.

The informal economy credit scoring model and solution aim to address the lack of access to credit for underserved communities, particularly women and those in rural areas. In Rwanda, savings and credit groups play a crucial role in providing financial services to low-income individuals and small businesses, but they often lack the resources to assess creditworthiness and offer loans at scale. This leads to a situation where many qualified borrowers are unable to access credit, stifling economic growth and leaving individuals and communities vulnerable to financial shocks. Furthermore, group members are unable to leverage their financial data and behavior within the group to access credit from other financial institutions, including MFBs, MFIs, and banks. 

According to the 2022 national  savings maps, there are 91,000 savings and credit groups with a total membership of 2.2 million in Rwanda. Among these members, 76% are female and 24% are male.

Some of the current issues of SCGs include:

• Lack of safety of their finances-since money is kept in their houses.

• Lack of access to faster payments and other quicker financial services as enabled by technology.

• Limited amount of financing from these groups that can't support their members to expand their businesses.

• No framework for financial consumer protection in this informal set-up

• Failure to transact remotely.

Despite Rwanda's large number of savings groups and the informal economy in general, traditional lending institutions have remained hesitant to lend to underserved communities due to perceived high risk or lack of credit history, further exacerbating the problem stated above. 

A credit-scoring solution targeted at savings and credit groups/members can address this problem by providing a data-driven, objective way to assess creditworthiness and streamline the loan application process, increasing access to credit and promoting financial inclusion for underserved communities in Rwanda and sub-saharan Africa..

An automatic credit-scoring algorithm embedded in SAVE by Exuus; digital savings group solution will seamlessly streamline the lending process and enable savings and credit groups to assess creditworthiness quickly and objectively.

Manual credit assessments are often time-consuming, labour-intensive, and subject to human bias, leading to inconsistencies in the lending process. By using an automatic credit-scoring algorithm, savings and credit groups can standardize their credit assessment process and reduce the risk of errors or bias. This can help to increase the efficiency of the lending process, making it easier for members to access credit and for the savings and credit group to manage its loan portfolio.

Furthermore, using an automatic credit-scoring algorithm can also help to reduce lending risks and improve the accuracy of credit assessments. The algorithm can analyze various data points, including past financial transactions, contribution and debt payment history, and other financial indicators, to assess the creditworthiness of borrowers. This can help savings and credit groups to make more informed lending decisions, reduce the risk of default, and minimize losses in addition to reducing the risk of third-party lenders such as banks and other financial institutions.

Figure 1: Technology workflow 

The target population of the SAVE credit score solution is 91,820 savings groups in Rwanda, comprising approximately 2.2 million individuals. These saving groups are mostly made up of low-income earners and small business owners who lack access to formal financial services, including credit, due to their lack of credit history, collateral, and high transaction costs.

Currently, these underserved individuals rely on informal financial institutions and money lenders for loans, which often come with high interest rates and limited credit options. This situation creates a cycle of debt, making it difficult for them to grow their businesses, access education and healthcare, and achieve financial stability.

Our AI-powered credit scoring solution aims to address these needs by providing a reliable and efficient credit scoring system that will enable saving groups to access affordable credit. The solution utilizes machine learning algorithms to analyze financial data, including savings history, loan repayment, and transaction history, to generate a credit score for each individual. This score will provide lenders with a measure of creditworthiness, reducing the risk of default and enabling lenders to offer affordable loans.

By providing affordable credit, our alternative credit score solution will enable savings group members to invest in their businesses, access education and healthcare, and achieve financial stability. This will have a positive impact on their lives and the wider community, creating economic growth and reducing poverty.

Exuus, led by Team Lead Shema Steve, is well-positioned to deliver this solution as they have been working closely with the National Bank of Rwanda and Access to Finance Rwanda to understand and track the Savings group landscape in Rwanda for the last decade. As a consultant to both institutions, Exuus has produced and maintains the National Savings group map hosted by the central bank. [https://sg.bnr.rw/map] Additionally, Exuus has worked closely with savings groups and NGOs working with the groups to develop a robust digital savings group solution, acquired licenses from the National Bank of Rwanda to expand their services, and entered into strategic partnerships to offer innovative micro-loan and micro-insurance solutions/products.

Furthermore, the Exuus team is mostly based in Rwanda, and they speak the three languages in Rwanda, including English, French, and Kinyarwanda. This close proximity to the communities they serve enables them to understand the needs of the target population and engage them in the development of the solution meaningfully. They have consistently found innovative ways to engage all stakeholders in their industry and have a deep understanding of the informal economy in Rwanda. [https://open.spotify.com/show/7A5Nvy4VJ1Zxoxud1RD7Bh?si=Gda7JVoMRw-1MSUBHWlGEQ|

The Exuus team's design and implementation of the solution are guided by the communities' input, ideas, and agendas. They work closely with savings groups and NGOs, ensuring that the solution is tailored to the specific needs of the target population. Exuus is at the forefront of developing the ecosystem of the informal economy in Rwanda and is committed to making a meaningful impact on the lives of the underserved population they serve.

106,588 people (74.7% are women)

There are 268 Solver teams across the world, with about 38 teams in Africa. Solve, therefore, has a deep understanding of the region and also boasts a strong startup community on the African continent.  Furthermore, the Solve venture thesis is focused on addressing the needs of the underserved across sectors. This suggests that MIT Solve has a strong understanding of the context of our innovation from a technical and geographic perspective.

As a Solver team, we face various technical, legal, cultural, and market barriers as we transition from the growth to scale up phase;  and we hope Solve can help us overcome through both monetary and non-monetary support. Specifically, we hope that Solve can help us with the following:

Technical Barriers: We hope that Solve can connect us with technical experts who can help us improve our innovation's technical features and capabilities. This includes advice on the best technology solutions and tools to use, as well as the development of software and hardware solutions that can support our innovation's scaling. The GSR foundation has a decade of deep crypto market expertise and a track record of making profound progress on behalf of our clients. This expertise would be very useful as we develop our AI and blockchain based credit scoring solution. 

Legal Barriers: We hope that Solve can help us navigate the complex legal and regulatory environment in the countries where we operate. This includes advising us on the regulatory requirements, licenses, and permits needed to operate our solution in different countries. Solve can do this through experts or other Solver teams operating in markets we will potentially expand into and their insight will be valuable.

Cultural Barriers: We hope that Solve can help us build trust and increase awareness of our solution in the target communities. This includes connecting us with community leaders and stakeholders who can help us understand the cultural nuances and preferences of the communities and stakeholders we serve.

Market Barriers: We hope that Solve can help us develop marketing strategies that can enable us to reach more customers and grow our user base. This includes connecting us with partners and solver teams who are already working with low income groups and provide us with market insights and help us expand our reach to underserved communities.

Given Solve's deep understanding of the African region, we believe that Solve is well-positioned to support our growth as our partner.

The booming digital lending market surpassed $300 billion in 2020, with significant growth coming from new smartphone users in emerging markets. Every day, millions of clients from Kenya to the Philippines use innovative fintech apps like Tala and Branch to access “instant loans” from their mobile phones. These digital lending apps analyze data extracted from the phones of prospective clients to make data-driven lending decisions without the need for loan officers or brick-and-mortar banks. For aspiring entrepreneurs in the developing world, these digital solutions can provide essential working capital that might otherwise be impossible to obtain from traditional lenders. 

Amidst all the success stories, however, are a growing number of concerns about the risky practices some digital lenders use to serve vulnerable clients in developing markets. A 2021 Center for Financial Inclusion blog by Maria Gabriela Coloma Ponce de Leon underscored this challenge, noting that “the primary problem is that digital lenders do not measure the capacity of someone to repay, but their willingness to repay, and these are drastically different concepts.” In this single sentence, the author focuses our attention on the critical question in digital finance today: How can digital lenders accurately measure the capacity of a client to repay in a low-cost, rapid and ethical manner?

One approach might be to establish the various income-generating roles a client undertakes and assign an earnings estimate to each role using some kind of earnings matrix. Government statistics could theoretically provide some of this information, but many countries do not publish useful earnings data, especially for the informal economy. In developed countries, data from credit bureaus is used to attach a confidence level to a borrower’s stated level of income, but these services are typically not available for most customers in frontier markets.

If estimates based on published data sources aren’t the answer, digital lenders could try to assess income levels directly. Unfortunately, the earnings of different clients vary greatly even within the same roles, either due to time spent, local variations or different levels of entrepreneurship. At best, this might help lenders weed out intentionally misleading loan applications, but collecting this information would create a highly discontinuous and “friction-full” client experience, which also has costs.

Even if digital lenders could generate an accurate earnings estimate, this approach requires another essential piece to the puzzle – understanding a client’s spending patterns. While some clues can be gained from analysing smartphone data, spending patterns are even more variable and harder to predict than income estimates. Add the possibility of compound inaccuracies in this approach, and the question needs to be asked: Is there a better way to assess ability to repay that is economical, universal and reliable?
 

OUR APPROACH: SAVING-LED DIGITAL FINANCE Part the answer may come from a new generation of “savings-led” digital finance apps that use the savings capacity of clients as a proxy for their ability to repay loans. Unlike “instant credit” apps, which can lead to over-indebtedness, these savings-led solutions start by helping clients build good saving habits. From the lender’s perspective, the primary benefit of this approach is that the clients themselves demonstrate how much surplus they have by how much they save and when. Instead of digital lenders estimating what clients can afford, each client’s track record of savings generates this information straightaway. A second clear benefit of the savings-led approach is that it encourages borrowers to build healthy saving habits, which inevitably builds financial resilience.

In the next 12 month (starting from June 2023), we are working towards achieving the targets below

• Number of groups reached: ~40,000 groups  

• Number of individuals reached: 1 Million 

• Number of credit partners onboarding: At least 5

• Number of credit scores issued: 500k (ideally equivalent to the number of our activer users estimated at a minimum of 50%)  

• Volume of credit disbursed: A ratio of 30% - 40% of our total users

• Value of credit disbursed:  A minimum of $500,000 

• Targeted domain (value chain of interest): smallholder farmers

• Gender ratio: 50%-60% of our micro-loans recipients should be women

As for the 5 year goals, ideally we should triple the above 12 months goals and expand to at least 4 more geographies.

Exuus has developed and operationalized a Monitoring, Evaluation and Learning (MEL) framework. This role is currently played by the communication  lead with support from a MEL expert on a project basis. We have experience developing MEL tools, collecting data, analyzing data, developing findings and communicating findings to improve our operations and project implementation.

A credit-scoring solution targeted at savings and credit groups/members can address this problem by providing a data-driven, objective way to assess creditworthiness and streamline the loan application process, increasing access to credit and promoting financial inclusion for underserved communities in Rwanda. See detailed theory of change below. .

Considering our saving-led approach, below is a brief explanation on how we scientifically and statistically go about our credit scoring process:

While statistically analysing this information, we generate data-driven credit scores that incorporate predictive relationships between a wide variety of factors, including the ratio of loans-to-internal savings and a member’s repayment performance.

As one might expect, our analysis shows that the higher the loan-to-savings ratio, the higher the probability of loan default. Our threshold analysis for groups in rural Africa, which looks at this variable in isolation, estimates that a loan-to-savings ratio of 1.35:1 best separates borrowers who repay loans on time from those who do not. In other words, group members who borrow $1.35 or less from the group per every $1 they’ve contributed in savings are less likely to pay late or default on their loans.

Another key finding is that the amount saved by a client is typically more important as a predictive indicator than the frequency of savings. Savings success, measured as the amount saved divided by the group maximum, is highly significant in predicting potential default, whereas savings frequency is far less relevant statistically. This finding is evident across different country data sets.

For group-based savings apps, our research suggests that other savings-led transactions are also statistically significant in predicting member loan repayment performance. These transactions include a member’s contributions to the group’s social fund (a separate savings pool for emergency use by members which does not have to be repaid), and fines levied by her group (for transgressions ranging from non-attendance at meetings, to non-contribution to savings and non-payment of loans). Given that these transaction types are entirely outside the scope of credit-led solutions, this is further evidence of the power of savings-led digital finance to measure a borrower’s capacity to repay.

BENEFITS AND TRADE-OFFS OF THE SAVINGS-LED APPROACH

There are, of course, some potential trade-offs of this approach. From a digital lender’s point of view, savings-led apps require more time to gather relevant data on each client. Instead of generating an instant quote, lenders engage with clients over a period of time, developing a trusted relationship rather than adopting a purely transactional approach. Credit-led digital finance may promise faster revenue growth out of the gate, but it often comes at the cost of putting some clients into debt stress. Savings-led solutions, by contrast, may result in slower growth, but they help clients build healthy financial habits and make it easier for digital lenders to understand each client’s true capacity to repay. In the long term, we believe the savings-led model is more sustainable for all parties.

Most importantly, we see a significant benefit to clients in terms of fair treatment, especially when it comes to the risk of putting borrowers into an unsustainable debt cycle. Savings-led digital lending may not deliver the instant gratification of “sign up and walk away with a loan” on first engagement. But for those willing to wait a little longer, we believe it will prove to be the better approach. Once that trust relationship is established and data starts flowing, the savings-led digital lender is equally able to deliver “instant credit” decisions, just like first-generation credit-led apps – yet with the advantage of superior data and lower risk for all parties.

We used a number of technics including but not limited to logistic regression, CART, KNN-Nearest Neighbour, machine learning technics, etc. These technics enabled us to come up with our initial score cards for both individual. & groups – this is an ongoing effort to ensure high efficiency at scale.

We run a successful pilot in Rwanda and obtained a micro-lending license from Rwanda's central bank as a result. Our plan is to scale this up in Rwanda and beyond. 

At Exuus, it’s important for us when hiring for our postings to seek out diverse candidates and consider factors beyond skills and potentials to ensure full inclusiveness. We also strongly believe in accountability where individuals and teams are held accountable for achieving their goals and objectives.

Lastly, we foster a culture of inclusion and respect within our team/workplace. This largely involves promoting open communication, encouraging diverse perspectives, and also celebrating diversity through events and various team activities.

The business model for our innovation is a B2C2B model, where savings groups can apply for credit through our SAVE marketplace. 

In summary, our business model is based on providing a marketplace for credit and charging a transaction fee for the service provided, as well as offering value-added services to our customers.

Our solution will charge a transaction fee of less than 0.5% of the credit value for the service provided. This fee will cover the cost of credit assessment and processing of loans.

Additionally, we plan to generate revenue by offering value-added services such as financial literacy training, insurance products, and other relevant services to our customers. These additional services will not only generate revenue for our business but will also enhance the overall financial health of our customers.

• So far we've raised + $850,000 in investments + grants
• Last year that ended in December 2022, we generated a net profit of $15,087.85 from net losses of $86,286.10 and $84,483.24 in 2021 and 2020 respectively
• This year we're projecting a gross revenue of +$450,000 and +1,052,000 in 2024.

In short our revenues are already covering our Opex, however grants and more investments are needed to de-risk our operations speed up our growth in Rwanda and beyond