Case study: Universal credit scoring for Female-led SMEs in Ethiopia

LenddoEFL collaborated with the World Bank Group to facilitate psychometric assessment for alternative credit scoring as part of the Women Entrepreneurship Development Project (WEDP) launched by the Government of Ethiopia.

The World Bank recently published an extensive and insightful report: “Designing a Credit Facility for Women Entrepreneurs Lessons from the Ethiopia Women Entrepreneurship Development Project (WEDP)”, which delves into different aspects of this project.

To download the full report please visit: https://openknowledge.worldbank.org/bitstream/handle/10986/34013/Designing-a-Credit-Facility-for-Women-Entrepreneurs-Lessons-from-the-Ethiopia-Women-Entrepreneurship-Development-Project.pdf?sequence=4

WEDP was launched in 2012 by the Ethiopian government with the aim of increasing the earnings and employment of growth-oriented micro and small enterprises (MSEs) owned or partly-owned by women entrepreneurs in Ethiopia. LenddoEFL was selected to

Following are selected extracts from the World Bank Report regarding LenddoEFL’s contribution

From Page 11 of the Report:

“WEDP provided a stable anchor from which to innovate, including drawing on financial technology (fintech) as a means to maximize the operational efficiency and effectiveness of lenders, while relaxing collateral constraints for women entrepreneur borrowers. The success of introducing a non-traditional credit assessment methodology to a low-tech and low-literacy environment like Ethiopia stirred enthusiasm and buy-in from the financial sector.

Financial institutions’ traditional lending methodologies often require data on loan applicants, including their tax records, credit history, financial statements, and legal status. MSEs in general, and women-owned MSEs in particular, often lack sufficient credit history, reliable financial statements, and collateralizable assets. This is compounded in emerging markets like Ethiopia, where there is an absence of proper financial sector infrastructure, such as a credit information system, which can help lenders identify credit-worthy borrowers. Faced with such limitations, financial institutions rely on unduly large collateral requirements to minimize their exposure and risk. This results in many women-owned MSEs being excluded from the financial system, while financial institutions miss the opportunity to tap into a pool of potential borrowers.

In recent years, there has been a tide of financial technology, or “fintech”, that has been sweeping across the global financial landscape, which has introduced new tools, systems and business models — allowing financial institutions to accelerate MSE lending in a profitable and cost-effective manner. In early 2014, the WEDP team began investigating different technologies that could address the collateral constraint by closing the information gap among MFIs. Among the promising technologies was one developed by the Lenddo Entrepreneurial Finance Lab (LenddoEFL), whose approach does not rely on traditional financial statements, business plans, high-value physical assets, or borrowing histories. Rather, their value proposition was a universal credit score that was calculated based on a psychometric tool that evaluates the entrepreneur’s personal attributes, including “locus of control, fluid intelligence, impulsiveness, confidence, delayed gratification and conscientiousness.” LenddoEFL’s technology allows for an applicant to complete a 45-minute self-administered test on a tablet computer to determine his or her eligibility for a loan. While this technology had been used in other contexts to help banks improve and/or expand their portfolios, WEDP was among the first initiatives to harness this technology as a substitute for fixed asset collateral. Moreover, for those applicants who already had collateral, the test was designed to allow them to qualify for a larger loan size.

To pilot the psychometric testing, the Amhara Credit and Savings Institution (ACSI) was selected, as it is the largest MFI in the country, with over 1 million active borrowers, 440 branches and individual loans comprising 10 percent of its portfolio. ACSI saw the LenddoEFL technology as an opportunity to improve their ability to screen for individual loans even beyond their WEDP portfolio.

Despite EFL’s great track record in Sub-Saharan Africa, Ethiopia’s context presented a unique challenge. In addition to translating the test into Amharic, LenddoEFL worked to include more visuals and interactive exercises to cater to ACSI’s low-tech and low-literacy clients. Moreover, while ACSI was enthusiastic about the psychometric testing, it was understandably hesitant about relying too much on the technology, given the lack of an evidence base in Ethiopia. As such, EFL focused on testing clients without using the resulting score as the basis for the credit decision – allowing ACSI to observe the accuracy of the test without taking on any credit risk.

In 2015, the psychometric test was pre-piloted in two ACSI branches in Bahir Dar with 420 interested clients, and then piloted across 12 branches with 2,496 clients. As loans matured, WEDP was able to track the progress of the loan repayments. The data revealed a clear trend between psychometric test scores and loan performance. Those borrowers who scored higher on the test were seven times more likely to repay their loans than lower scoring customers. Further results and details of the study are available starting on page 45. 

“Having succeeded with one of Ethiopia’s largest financial institutions, the pilot demonstrated that a psychometrics-based loan screening system could be developed in the country, pushing the frontier of credit access for hundreds of thousands of collateral constrained borrowers. The ACSI experience demonstrated to policymakers and private sector leaders alike that fintech can make a profitable and profound difference to the Ethiopian economy. ”

Based on the proof-of-concept from the ACSI pilot, other MFIs began requesting for the psychometric technology. In 2018, WEDP launched the LenddoEFFL screening system with Wasasa. In 2020, ADCSI followed suit. Around this time, as an added incentive, DBE began providing additional liquidity (named “WEDP X”) to support MFIs who were eager to test out alternative collateral products. Moving forward, WEDP is likely to build on this incentive mechanism to facilitate further crowding in by other microfinance institutions across Ethiopia.”

Source: The World Bank

---

Header photo by Stéphane Hermellin on Unsplash

Mondato Feature | Can Personality Predict Loan Performance

LenddoEFL has been featured by leading FinTech consultants, Mondato, in their Insights Series.

---

Know Your Customer — often abbreviated as KYC — is such an important part of success in digital finance that it almost deserves to be canonized into KTC: Know Thy Customer. Indeed, creating “bank-legible” forms of identity authentication, streamlining methods of verifying it, and tailoring business strategies around it — all of these entail an enormous range of regulatory and business challenges, from data privacy to algorithmic discrimination. In evaluating the promises of alt-data for banking thin-file customers, this week’s Insight explores the promises and perils of psychometrics as a way of evaluating would-be lendees.

Know Thy Customer

The first maxim adorning the mythical Delphic Temple of Apollo in Ancient Greece, famously, is “Know Thyself.” In business, however — particularly in the business of lending — it is easy to see why the first law may rather be ‘know thy customer.’ In the US, knowing who to lend to was revolutionized in the 1950s when an engineer and a mathematician teamed up in California to generate the first ‘credit score’ — today known as a FICO score — factoring a number of data points around payment history, amounts owed, length of credit history, types of credit used, and more.

The success of this system spread throughout much of the world, and though the precise ways in which each national jurisdiction has developed or regulated credit scoring varies significantly, the art of recouping loans has become much more of a science: the science of quantifying a specific individual’s likelihood to repay a loan under a given set of assumptions or circumstances.

Here, traditional credit bureaus (think EquiFax, Transunion, and Experian in the US) have historically played a major role in the development of retail bank credit. The World Bank deemed the model good enough for export, and has been promoting the development of private credit bureaus in emerging markets since 2001. The record, evaluated by any number of dimensions, is mixed at best; as of 2019, private credit bureaus cover just a third of adults globally, with gaps in coverage unsurprisingly concentrated in lower-income countries.

Indeed, while such forms of credit assessments (for better or for worse) lie at the center of retail finance in formal economies, the paradigm presents serious challenges in emerging markets. Given the paucity of ‘bank-legible’ financial histories in the informal sector, would-be loan applicants in Africa, Asia, or Latin America seeking a loan from a traditional bank might find their hopes and dreams of home-ownership or entrepreneurship at the mercy of a faceless bank bureaucrat judging their ‘worthiness’ on nothing but their gut — or, worse, their biases and stereotypes.

Enter alt-data. The digital era has spawned entirely new forms of understanding people’s behavior through the combination of new forms of data generation and algorithms that can identify hidden correlations between ‘user attributes’ and payment outcomes. In other words, given the appropriate data inputs on an individual and the larger population — as well as judicious interpretation — big data and machine learning can yield actionable, predictable outcomes.

But from whence is this alt-data mined, and is it reliable? Our phones, naturally, can provide a ready trove of information about us, and given their ubiquity even among the world’s poorest, they’re increasingly being leveraged for purposes both benevolent and nefarious. Same goes for satellite data — like all powerful tools, they are double-edged.

Source: UC Berkeley Center for Long-Term Cybersecurity, 2020

Psychometrics, however, are fundamentally different from other alt-data sources in at least two ways: firstly, there are less privacy concerns since psychometric data can only be collected with the potential lendee’s consent — and without the use of labyrinthine terms and conditions agreements that often obscure data mining operations — given that they are administered as a questionnaire. Secondly, while not everyone has a cell phone or uses it extensively, everyone’s got a personality.

Alt-Data Streams of Consciousness

Psychometrics occupy a particularly sensitive — and almost mystical — place among sources of alt-data. This is due, at least partly, to the fact that the entire field of psychology has sustained fundamental challenges in recent years. Against a canonical understanding of “homo economicus” as a utility-maximizing rational actor, the sub-discipline of behavioral economics has been gaining traction as a more rigorous way of understanding, predicting and even influencing human behavior.

Similarly, the past few years have uncovered a systematic bias among swathes of psychology experiments that universalize generalizations drawn principally from studying populations in Western, Educated, Industrial, and Democratic — aka WEIRD — countries.

““Decades of psychological research designed to uncover truths about human psychology may have instead uncovered truths about a thin slice of our species — people who live in Western, educated, industrialized, rich, and democratic (WEIRD) nations.””

— Beyond Western, Educated, Industrial, Rich, and Democratic (WEIRD) Psychology: Measuring and Mapping Scales of Cultural and Psychological Distance, 2020

Meanwhile, pop-psychology theories further invite skepticism, like the infamous “Color Test.” Such tests aim to simplify personality traits into neat, discrete and stable categories, purported to determine romantic, amicable or professional compatibility between individuals. Even popular tests like the famous Myers-Briggs Test, however, mostly fail to stand up to snuff when the empirical rubber meets the road of statistical significance — for most Human Resource departments, the most charitable assessment of such tests has been summarized as “not entirely useless.”

But psychometrics for credit-lending deserve a hard look, if for no other reason than the endurance of LenddoEFL in the marketplace.

LenddoEFL is perhaps the oldest and best known outfit providing psychometric credit scores. The product of a merger between Harvard research-incubated Entrepreneurial Finance Lab and Lenddo, a Singapore-based smartphone data credit specialist, the two companies joined forces in 2017 and claims to have facilitated over two billion dollars in loans across the more than 20 countries in which it has operated. Its proprietary tests are broadly based on the most rigorously evaluated psychometric frameworks in academia: the “Big Five” personality traits of extraversion, conscientiousness, agreeableness, neuroticism and openness to experience.

The case for psychometrics qua credit-scoring, however, has a fairly major bona fide when it comes to evaluating loan-performance: market proof. An independent World Bank evaluation of a LenddoEFL collaboration with Superintendencia de Banca y Seguros (SBS, the fifth largest commercial bank in Peru) using data from June 2011 to April 2014, concluded that psychometric scores were indeed practicable for identifying ‘good lendees’ that traditional assessments would otherwise pass on:

““Banked applicants accepted under the traditional credit scoring method but rejected based on their EFL score are 8.6 percentage points more likely to have been in arrears for more than 90 days during the 12 months after being screened by the EFL tool, compared to 14.5 percent of entrepreneurs who are accepted using both methods … results suggest that the EFL tool can be used to offer loans to unbanked applicants who are rejected under the traditional method without increasing the risk of the loan portfolio.””

— World Bank evaluation report of LenddoEFL pilot in Peru

The evaluation is narrow in its findings, but it lends strong evidence that rigorously developed psychometric tests are able to add a layer of KYC granularity in identifying individuals who are both able to generate enough cash flow to service their debt and who are willing to repay their debt.

All Data is Credit Data

While an increasing number of financial institutions and fintech players are learning to integrate alt-data feeds into their KYC processes, psychometrics remain an edge case. Nonetheless, a handful of psychometric providers have gained traction around the world, like Innovative Assessments based out of Israel (though with a large global footprint), or GFI, focused on the Malay market. A commonality across psychometric providers appears to be founders with a long and established track record in academia and social science research methods. This perhaps explains why there aren’t more psychometric companies out there; amidst the aura of mind-reading in a psychometric business pitch, investors are typically reassured that the product is literally built by a PhD holder. However, these are not necessarily the individuals known for building and scaling companies and products.

James Hume and Jabu Sithole, respectively the Chief Operating Officer and Head of Modelling at LenddoEFL, reflect on this particular challenge in their own company’s history. They note that the secret sauce in creating a successful psychometric-for-lending business is not in understanding or quantifying ‘personality’ per se, but rather in ruthlessly testing correlations within data sets comprised of carefully collected character attributes, and — critically — intelligence on ‘bads,’ or lendees who default on their obligations.

““The key is to ask the right question. Our primary driver is not to understand personality. We are laser focused on correlations and predictability, specifically around repayment.””

— James Hume - COO, LenddoEFL

““When we ‘train the model,’ what we are doing is using historical data to decipher historical patterns and project into the future. But if you lack ‘bads’ in certain segments you examine, then it’s hard to get a sense of who will default. So to begin with, we need sufficient sample size and representativeness, and different characteristics to generate confidence. This can take time — between 6-9 months.””

— Jabu Sithole - Head of Modelling, LenddoEFL

This process necessarily entails a learning curve for each new market — after all, no one is claiming that Nigerians who score the same on questions testing conscientiousness or confidence will behave the same way as Chinese applicants with the same scores. But part of the secret sauce also comes with measuring how people answer, not just what they answer.

Indeed, the time an applicant spends on a question can itself provide an additional data point to feed into the credit-algorithm. Mondato has previously explored how such “autogenic” data processing techniques have proven effective in predicting who will churn in an IFC-Mastercard report on account dormancy last year, and it perhaps bears repeating that when it comes to machine learning for human behavior, human decision-makers often need to relinquish the “need to understand in order to satisfy the need to predict.”

Personality as Product?

So if personality traits can reliably be measured in ways that can help the unbanked gain access to credit, why haven’t such tools become ubiquitous? For starters, there is still a lot of market education to be done. Traditional models are already fairly good at identifying great loan applicants and terrible ones; it’s in the segment of ‘average’ lendees, or those at the margin, that there is the most room for improvement — and most banks don’t even make most of their profits through retail lending in the first place. Incrementally improving their lending models — while improving financial inclusion — is not going to rock their bottom lines, and thus creates significant bottlenecks to uptake.

Secondly, ‘productizing’ alt-data for lending is still a relatively niche use-case. While the idea holds a lot of promise, particularly as digital identities become more and more critical to long-term customer relationships, a profitable business model for offering B2B alt-data credit scoring is yet to be fully cracked. Simply put, developing and incessantly refining behavior-predicting algorithms isn’t free, nor is it cheap.

Subsequently, LenddoEFL recently simplified its pricing model, lowering upfront engagement costs in favor of recurring service charges. The gamble is that the service can provide value to lenders immediately (for example around cross or upselling opportunities) and on an ongoing basis, rather than charge a big lump-sum up-front for a model that only starts to yield fruit in half a year. In this way, it hopes to generate more value to clients and more revenue streams for itself even before the full repayment picture needed to calibrate the model for its primary purpose — identifying ‘invisible good bets’ — is even completely baked.

Nestled at the heart of “alt-data for inclusion” narratives are fundamental ethical questions. As researcher Rob Aitken reminds us, inclusion projects often constitute troubling new kinds of social sorting and segmentation:

““Experiments in alternative credit scoring are, in some essential measure, attempts to know the unbanked – to know unbanked bodies, payment traces, psychological inclinations, online behaviour, social footprints – and to verify the creditworthiness of those bodies in detailed and intimate ways. The body becomes itself a kind of ‘database’ from which some sort of content is extracted or “captured,” then algorithmically encrypted and sorted for retrieval.””

In lightly regulated environments, consumer protections are all the more important, particularly given the ominous implications of racist, sexist or neocolonial artificial intelligence. And yet, hope remains that models will evolve that put people in charge of their own information, and in this sense psychometric evaluations may represent a uniquely powerful modality of respecting unbanked or underbanked individuals’ privacy, dignity and agency. Can we imagine a future where all consumers will be empowered not only to control and protect their data, but perhaps even to monetize it according to their own needs, desires, freedoms or aspirations? Perhaps the first seeds can be found in tools that allow people simply to learn as much about themselves as others are collecting. The Oracle at Delphi, surely, would agree with this virtue.

Photo by The New York Public Library

If you would like more information about the use of psychometric testing for credit scoring, please contact us.

LenddoEFL puede predecir el riesgo, pero ¿les gusta a nuestros clientes? MicroBank evalúa la usabilidad de LenddoEFL y el impacto en NPS

(English version below)

MicroBank, la entidad financiera española líder en microfinanzas en Europa, está evaluando constantemente sus procesos de cara al cliente, respecto a la usabilidad y la aceptación del usuario, una forma de actuar que supone una de sus prioridades. Cuando el banco desarrolla una innovación, se aplica el mismo nivel de escrutinio.

 Entonces, cuando MicroBank decidió usar LenddoEFL para evaluar el perfil crediticio emprendedores para acceder a préstamos, el despliegue estaba condicionado a una experiencia positiva de sus clientes.

 MicroBank empezó a medir la usabilidad del cuestionario de LenddoEFL, su impacto en el Net Promoter Score (NPS) con respecto al uso del microcrédito convenio entidades y cómo la gente se sentía al hacerlo.

 Para nuestro agrado, encontramos que el cuestionario de LenddoEFL es fácil, comprensible y de duración apropiada. Acá se observan algunos puntos relevantes:

• NPS: 84%, superando ampliamente nuestras expectativas

• Satisfacción global:  9.16 de 10

• Idoneidad: 82% encontró el cuestionario adecuado para evaluar a prestatarios del segmento micro. Esto es excelente comparado a las herramientas de la mayoría de los bancos, pero, obviamente, no dejamos de lado al 16% que no encontró el cuestionario adecuado. Nuestro equipo de producto trabaja 24 horas (literalmente, somos un equipo global) para mejorar constantemente nuestra evaluación de crédito – haciendo el contenido más fácil, más divertido, más rápido de completar, más predictivo y conveniente para todos los niveles de alfabetización y manejo de tecnología.

• Duración: Más del 70% encontró que el cuestionario tiene la duración correcta. Esto es bueno, pero queremos mejorar.

• Facilidad de uso: Más del 95% piensa que el cuestionario de LenddoEFL es fácil de completar.

MicroBank es un cliente exigente y este proceso nos ha ayudado a aprender y mejorar. Mientras que las noticias financieras están llenas de fintechs ayudando a bancos, este es un gran ejemplo de un banco mejorando a una fintech. Estamos muy contentos de que los resultados sean mejores de lo esperado, especialmente en un país como España, donde el acceso al crédito es generalmente bueno y la gente espera que el proceso se dé con la mínima fricción. Más aún, apreciamos que MicroBank nos haya desafiado para asegurar que nuestras herramientas superen las expectativas de sus clientes.

Esto nos hace mejores.

---

Para descargar el white paper completo por favor ingresa tu dirección de correo electrónico debajo.

---

LenddoEFL can predict risk, but do our clients like it? MicroBank evaluates the usability of LenddoEFL and the impact on NPS

MicroBank, the leading Spanish financial institution in microfinance in Europe, is constantly testing its client processes, regarding usability and user acceptance, ensuring these are always top priorities. When the bank launches an innovation, the same level of scrutiny applies.

So, when MicroBank decided to use LenddoEFL to assess the credit profile of entrepreneurs to access loans, the rollout was conditional on a positive customer experience.

MicroBank began to measure the usability of the LenddoEFL questionnaire, its impact on the Net Promoter Score (NPS) regarding the use of entities agreement microcredit, and how people felt about doing it.

MicroBank found the LenddoEFL questionnaire to be easy, understandable, and of appropriate duration. Here are some highlights:

• NPS: 84%, far exceeding our expectations

• Overall satisfaction: 9.16 out of 10

• Adequacy: 82% found the appropriate questionnaire to evaluate micro-segment borrowers. This is excellent compared to the tools of most banks, but obviously we will not leave out the 16% who did not find the questionnaire suitable. Our product team works 24 hours (we are literally a global team) to constantly improve our credit assessment - making content easier, more fun, faster to complete, more predictive and more suitable for all levels of literacy and access to technology.

• Duration: More than 70% found that the questionnaire was the right length. This is good, but we are working to reduce this.

• Ease of use: More than 95% think the LenddoEFL questionnaire is easy to complete.

MicroBank is a demanding customer and this process has helped us learn and improve.

While the financial news is full of FinTechs helping banks, this is a great example of a bank improving a FinTech. We are very happy that the results are better than expected, especially in a country like Spain, where access to credit is generally good and people expect the process to take place with minimal friction. Furthermore, we appreciate that MicroBank has challenged us to ensure that our tools exceed their customers' expectations.

This makes us better.

Mondato Webinar Series: Innovative Approaches to Digital Payments

As many in-person events remain on hold due to COVID-19, industry experts, Mondato have joined forces with the MEF to host a webinar series tackling the discussion of ‘the new normal’ across the payments industry.

LenddoEFL was invited to join a webinar to discuss innovative approaches to commercializing digital payments. The panel also included thought leaders from Mondato and Standard Chartered Bank.

LenddoEFL VP Corporate Development, Camille O’Sullivan joined the panel to discuss how LenddoEFL uses alternative data to link lenders to good borrowers.

As discussed, there are different ways that alternative credit scores can be used. As highlighted by Judah Levine from Mondato, alternative credit scores can even be complementary to traditional scores and there’s a feeling that using alternative data is becoming more and more mainstream.

At LenddoEFL, we work with customers that use alternative credit scores in different ways depending on the market and business case. Alternative Credit Scores can be used either as a proxy in place of a traditional credit score, or in conjunction with traditional methods. Some financial institutions are using alternative data to reassess thin file customers that have been soft rejected using traditional credit scores.

While for lenders that are already using traditional bureau scores, alternative credit scores can be used to lift the predictive power of a traditional credit score. One of the reasons that alternative data can be valuable in conjunction with a traditional bureau score is because of its low correlation.

Watch the full webinar at the link below:

https://www.mondatosummit.com/mondato-webinar

LenddoEFL joins Oxfam webinar for launch of B Ready study

This week LenddoEFL was invited by Oxfam Pilipinas to join a panel for the official launch of their Disaster Risk Financing study. The study is part of the B Ready initiative. 

The B Ready project was launched in 2019 and is the first line of defence for communities in disaster preparedness. 

Located in the Pacific Ocean typhoon belt, the Philippines is hit by up to 20 typhoons each year. While we have no control over these disasters we can help to both protect and prepare people and communities. Each and every one of us can be part of the solutions. 

The B Ready project has two pillars, digital weather forecasting and modelling for early warning, and digital financial technology to allow financial resources to reach those most in need.  

During the webinar, Oxfam explained the importance of credit-risk sharing for communities in disaster-prone areas, particularly those normally excluded from the financial ecosystem. 

Both governments and NGOs are supporting micro-finance institutions and financial service providers that provide loans to these communities by guaranteeing a portion of their loan portfolio. This helps to build the appetite for institutions to lend to these communities.

The FinTech sector is another stakeholder that can provide solutions for communities looking for ways to access credit and prove credit-worthiness. 

LenddoEFL APAC Sales Director Judith Dumapay explained how alternative data can be used to provide an indication of credit-worthiness for those with no or limited access to traditional financial data. Anyone who is online or carries a cell phone shares information whenever they interact with the device. This information can be analysed to understand who they are and their creditworthiness.

Watch the clip of LenddoEFL’s participation below:

Oxfam states that they have greatly relied on the power of collaboration to achieve their goals. LenddoEFL is proud to have partnered with Oxfam several times over the years to support the important work they do in the Philippines and around the world. 

You can view the whole video on Facebook here: https://www.facebook.com/OxfamPilipinas/videos/536358581093393/

Photo by Louie Martinez on Unsplash

LenddoEFL recognised among top finance companies in Singapore

LenddoEFL has been recognised by Welp Magazine as one of the top finance companies in Singapore in 2021 for its use of alternative data to provide credit scores and digital verification.

The list features startups and companies are taking a variety of approaches to innovating the Finance industry, but are all exceptional startups and companies well worth a follow.

To view the list go to: https://welpmagazine.com/these-are-the-top-finance-companies-in-singapore-2021/