Blog | Turning Gini into Profits

Written by Rodrigo Sanabria, Director Partner Success, Latin America

On a prior post by Carlos del Carpio (“The Economics of Credit Scoring”), we discussed the business considerations to assess the merit of a risk model. In this post, I will address how a good origination model impacts the bottom line of a company’s P&L.

These principles may be adapted to look into other types of models used at later stages of a loan life, but on this post we will only address loan origination.

From a business point of view, an origination model is a tool that helps us aim at the “sweet spot”: where we maximize profits. A simple way to think about it is as a trade-off between the cost of acquisition (per loan disbursed) and cost of defaults (provisions, write-offs): The higher the approval rate, the lower the cost of acquisition, but the number of defaults go up.

How do we go about finding the sweet spot? I’ll try to explain it below.

Figure 1

A good model has a good Gini. A “USEFUL” model creates a steep probability of default (also known as PD) curve – we usually refer to it as a “risk split”.

Figure 1 shows the performance of a model based on psychometric information used by an MFI. The Gini (not shown in the graphic) is pretty good (0.28). The risk split is great: the people in the lower 20% of the score ranking are about 9 times more likely to default than those in the top 20%.

Knowing the probability of default for a given group, we may set a credit policy. Basically, we need to answer: “what would the default look like given an acceptance rate?”

Figure 2

We have re-plotted the same data in Figure 2, but now we express the probability of default in accumulated terms. Basically, the graph shows that if we were to accept 80% of this population sample, we would have a 4.5% PD, but if we were to accept 40%, the PD would go down 2 points to 2.5%.

Now, from a business point of view, we still do not have enough information to decide. Do we?

Where would the profit be maximized?

The total cost of customer acquisition is mainly fixed. Whatever we spend on marketing and sales to attract this population, will not change if we reject more or fewer applicants. So, the cost per loan disbursed would grow as we reduce the acceptance rate.

Of course, the higher the acceptance rate, the larger the portfolio, and the more interest revenue we get. BUT, the higher the provisions and write-offs. The combination of these 2 variables (cost of acquisition and net interest income) produces an inverted U-shaped curve that uncovers the “sweet spot”

Figure 3

The current credit policy is yielding a profit at 100% acceptance rate (see Figure 3) because the sample being analyzed corresponds to all the customers that were accepted (i.e. we have repayment data about them). So, the portfolio is profitable.

But the sweet spot seems to be shy of 60% acceptance rate. If this FI were to cut down its approval rate to that level, profits would increase by about a third, and its return on portfolio value would almost double. Of course, there are other considerations around market share and capital adequacy that may play a role in such a strategic decision, but the opportunity is clearly uncovered by the model.

In my experience, the sweet spot usually lies within 30%-70% acceptance rates, driven by marketing expenditures, interest rates, cost of capital, sales channels, and regulation.

What if the shape of the curve shows a continuous positive growth? The sweet spot is at a 100% acceptance rate! – have we reached risk karma? – Most likely, the answer is no (but almost!).

Figure 4

Most likely, we are leaving money on the table. Some business rule may be filtering people before they are scored. I have experienced this situation while working with lenders. For example, a traditional bank was filtering out all SMEs that had been operating for less than X years. This bias in the population was creating a great portfolio from a PD point of view, but there was clearly an opportunity to include younger businesses. As you can see in Figure 4, the maximum return on the portfolio was achieved at 60% approval rate, but they could increase profits by approving beyond the current acceptance rate. Depending on their cost of capital, it may be a good idea to expand the portfolio by approving more people.

In summary, think of your origination model as a business tool. Don’t stop at looking at Gini to assess a model’s merit. Understand how your profitability would be impacted by changes in your acceptance rate. If the PD curve is steep enough, you may capture quite a lot of value by applying the model to either reduce or increase your acceptance rate.

CFI.Org | To Bank the Unbanked, Start Using Alternative Data

Capturing digital footprints using psychometrics can help FSPs reach the unbanked.

By Rodrigo Sanabria, Partner Success Director, Latin America, LenddoEFL

Originally posted on the Center for Financial Inclusion's Blog.

In a recent post on her report, Accelerating Financial Inclusion with New Data, Tess Johnson highlighted the huge opportunity that alternative data represents for the future of financial services. The simple fact that mobile and internet penetration have surpassed financial services penetration in most emerging markets hints at a big opportunity: many people who have had no meaningful access to formal financial services are creating digital footprints financial service providers can capture and analyze to reach them with commercially viable services that help them improve their lives. This prospect is also made possible thanks to machine learning and big data methods that were not available to us a few years ago.

Field team testing its psychometric credit assessment in Mexico. Credit: LenddoEFL

For those of us in the world of financial inclusion, these are very exciting times: the simultaneous emergence of online penetration and data analysis methods is generating an opportunity that our predecessors in this field couldn’t even have imagined.

The bad news is that harnessing digital footprint data using machine learning is not easy; it requires time, commitment and skills that are in short supply. However, the good news is that those with the vision and  endurance to leverage this opportunity will build a competitive advantage that will be sustainable for years to come.

When developing an alternative credit score based on traditional information (e.g., demographics, repayment data), analysts usually have historical data to design and train models. Through back testing, the credit scoring model is applied to historical data to see how accurately it would have predicted the actual results (i.e., loan repayment). We can get a pretty good sense of how the model will perform in the future and set up a credit policy accordingly. Yet, when we cannot use such traditional data sources, we are entering into uncharted territory.

Lacking prior information about our current customers’ psychometric profile or digital footprint, we must build those data sets from scratch. Depending on the data source, we may need very large data sets to compensate for the lack of data structure (unstructured data is simply data that is not easily accessible in a format or structure, like an Excel spreadsheet, that is optimal for generating insights). Just as with all other artificial intelligence applications, the more data you collect, the more predictive and stable your algorithms become. LenddoEFL is an example of an organization that gathers data for these profiles and footprints. It is an alternative credit scoring and verification provider that uses psychometric and other data about a loan applicant to determine a credit score and verify identity.

Furthermore, even state-of-the-art alternative data sources do not necessarily allow you to build models that are stable and reliable across multiple segments of the market. Therefore, you need to build algorithms that are specific to your target population.

One of the most challenging issues when implementing alternative data scoring initiatives is showing the results that can be achieved within a given set of time and budgetary constraints. In the long run, after the portfolio has matured, you can show whether using alternative data allowed you to approve more applicants within your target default levels, controlling by business cycle. But if you are working with 24- to 36-month loans, it may take three or four years before you can fully assess the impact of using alternative data, by which time internal attention spans may have already run short.

To account for that, LenddoEFL uses early indicators of model performance. We set a target maturity and days in arrears according to a financial institution’s portfolio’s profile, for example, 60 days in arrears within the first 9 months. Then we calculate a Gini coefficient—a scale of predictive power that can help lenders understand how good its credit score is at assessing who will repay and who will default on a loan (not to be confused with the Gini coefficient that measures income inequality) for the model as applied to that portfolio. (For more details on how to use the Gini, check out our blog series from our risk and analytics team: Part 1, Part 2, Part 3).

Is it too late to pursue an alternative credit scoring initiative? I would say yes, there are plenty of companies already doing this—Te Creemos in Mexico, Mynt in the Philippines and Business Partners in South Africa—but only a few lenders are utilizing alternative data in each market. You could be the first institution in your segment and country to implement such an initiative, and you can still take advantage of others’ experiences and learning.

The sooner you start collecting data and building models, the sooner you will be able to underwrite the unbanked segment better than your competition, and the longer the window of advantage will be. For those who start late, catching up with the early adopters will be a great challenge.

Read article on cfi-blog.org

Blog | Lessons from the field: How we created new group psychometrics to increase financial inclusion in Mexico

While Jonathan takes notes, Gerardo helps an applicant navigate our psychometric assessment on a mobile device. An essential component of our field work was to get direct usability feedback from applicants as they completed new psychometric content.

By Jonathan Winkle, Behavioral Sciences R&D Manager, LenddoEFL

An experimental psychologist by training, I am relatively new to the world of financial technology. Since joining LenddoEFL, I have embraced terms like information asymmetry, alternative data credit scoring, and financial inclusion. Yet it was only during a recent trip to the field that I was able to meet the people behind the FinTech jargon we use in our day-to-day, the small business owners whose lives we help improve in our mission to #include1billion.

In April of this year, I traveled with colleagues to Veracruz, Mexico to test new psychometric content for one of the top 3 microfinance institutions (MFI) in the country. Their group loan product extends a line of credit to a collection of business owners, but liability for payments is joint: if one person misses a payment, the group must still make that payment in full. Since many of those applying for these loans lack traditional credit histories, this MFI asked LenddoEFL to develop psychometric exercises that could quickly and reliably assess group traits that predict creditworthiness.  

There are traits that define a strong social group which are nonexistent for individual borrowers. A successful group has strong internal relationships that ensure they will help each other in times of need. A tenacious group can generate creative ideas to solve problems that arise when life presents hardships, as it is wont to do. And a cohesive group exhibits decision making abilities that allow it to act deliberately and with confidence. We designed new psychometric exercises to measure these core traits, and tested them in the field with groups of small business owners applying for loans.

Hiding from the Veracruz heat underneath a family’s palapa, Gerardo leads a collection of applicants through our group psychometric exercises while Jonathan makes observations about their behavior.

Measuring interpersonal relationships through social pressure
To measure the strength of a group’s interpersonal relationships, we examined the social pressure that exists among group members. Do individuals feel that they can answer sensitive questions honestly? Or do they feel pressure to conform to the opinions of the group majority? While the group was sitting together in one room, we asked them to raise their hands if they agreed with statements about the trustworthiness, fairness, and helpfulness of their local communities. We then asked individuals to answer these questions privately. The discrepancy between how the questions were answered in each setting could reveal how much social pressure exists, and thus how comfortable group members are being honest with each other. We expect that less social conformity means the group’s interpersonal relationships are stronger, an important factor for predicting whether the group will cover individuals who may miss payments throughout the loan cycle.

Measuring creativity through brainstorming
To measure a group’s creativity, we created a set of generative exercises. For both an easy and a hard problem, we had groups brainstorm as many solutions as they could in 60 seconds. The number of solutions generated was recorded as a creativity metric, and, as predicted, groups generated many fewer ideas for the harder exercise. We were also interested in the group’s dynamic as they performed these tasks. Were they apathetic or engaged? Was there a dominant member of the group? Ultimately, when a loan payment is due and some individuals are short on money, can the group come up with ideas for how to get the extra money? We hope that these generative exercises will shed light on this critical group trait.

Gerardo snags a picture with one of the applicants we met and her business, a stand selling eggs, candy, and other sundries. The small scale of some businesses we encountered, such as the one pictured above, reinforces their need for access to financial products. This woman’s entrepreneurial endeavors are only limited by the capital she can acquire.

Measuring decision making abilities through consensus
To measure a group’s decision making abilities, we created a time-to-consensus task. This exercise asks the group to solve a problem where all members must agree on the answer they provide. While we asked the groups to estimate the population of the state they live in, we actually don’t care how accurate their answer is! What’s more important in this exercise is how the group reaches consensus. Are they indifferent and accept the first estimate suggested? Or do they take their time and argue intensely while deliberating over possible solutions? What kind of strategies did they use to reach their estimate? Importantly, this task provides loan officers with a window into the group dynamic that might not otherwise be seen if the assessment merely collected static information such as sociodemographics and business revenues.

Financial inclusion is the mission of LenddoEFL, but working directly with the people we want to include allowed me to better understand how our assessments must be tailored to their cultures and experiences. The better we can measure group dynamics that predict creditworthiness, the more successfully we can extend financial services to those in need. As we continue to expand our credit scoring offerings across the world, looking past the business jargon we use and maintaining empathy for the humans we touch is essential on our path to #include1billion.

Blog | What exactly do we mean when we say financial inclusion?

LenddoEFL Partner Success Manager, Gerardo Rivero, doing field research for our financial access tools

We started LenddoEFL to solve the problem of access to credit in emerging markets, where people find themselves unable to get a loan, and unable to build their credit. This excludes good people from financial services, limiting opportunity for individual livelihoods and economic growth. 

We realized that even though people may have limited financial data in a credit bureau, they have plenty of unique data that can be accessed to better understand who they are. For example, we found that analyzing the digital footprint of an individual (with full consent) helps us to get to know them and understand certain traits that relate to creditworthiness and credit risk.

Now, we are working with banks and lenders across 20+ countries to use non-traditional forms data - digital footprint, mobile behavior and psychometric to predict risk, and unlock access.

When we think about financial inclusion, there are really 3 levels, each necessary to get to the next one. 

1. Access comes first: Can you get a credit card or open a savings account? 1.7 billion adults around the world lack an account at a financial institution according to the 2017 Global Findex. Enabling these people to take that first step towards opportunity is foundational. 

2. Price: Often where access is scarce, the first loan can come from a payday lender or other institution at an unbearably high price/interest rate. So the next step to financial inclusion is bringing the price of a loan down to reasonable rates even without historical credit data. 

3. Convenience: Once you have access to credit at a fair price, the third step to financial inclusion is making it convenient to get. Historically, inclusive lending such as microfinance could involve arduous, time consuming processes with multiple in-person visits and copious document collection. We want to make borrowing easier and faster for people while maintaining safety. The beauty of moving from analog loan officer-based processes to machine learning and big data-driven processes like ours is that it becomes faster and easier. 

We believe that financial inclusion isn't simply about access to financial products, but about access to fast, affordable, and convenient financial products. Join us on our mission to #Include1Billion people around the world. We are hiring! 

Welcoming our New Behavioral Science Manager

In this photo, Jonathan demonstrates cultural differences in height during a field visit with loan applicants in Veracruz, Mexico.

Since our merger, we have welcomed a number of incredible new colleagues onto the LenddoEFL team. Jonathan Winkle joins us in our Boston office as our new Behavioral Science Manager. We cornered him to learn more.

Tell us about your background?

In undergrad I majored in psychology, where I developed a passion for researching the brain and behavior. To gain more experience after college, I worked in a systems neuroscience lab at MIT studying visual attention. Eventually I found my way to Duke where I earned my PhD in cognitive neuroscience. My dissertation focused on the behavioral economics of dietary choice, investigating how the mind is affected by “nudges” that can bias people towards healthy (or unhealthy) eating habits.

What brought you to LenddoEFL?

Studying behavior has always excited me because it is the ultimate endgame of our brains’ hard work, yet academic research on the topic can often be too disconnected from real-world problems. I found myself wanting to make more of an impact on society, and in this role I can leverage my experience to quickly and directly improve people’s lives around the world. As the Behavioral Science Manager for LenddoEFL, I can test a new hypothesis and apply that knowledge globally in a matter of weeks. And the better I do my job, the more people I can help get access to life-changing financial services.

What are your plans as Behavioral Science Manager?

My primary goal is to drive feature engineering. Features are the observations we collect about individuals to predict credit risk, and feature engineering is the process of discovering and creating new features to make our algorithms work better. For example, how honest a person is might be predictive of loan default, but we first need to quantify honesty as a feature to use it in a predictive model. As new features make our models more predictive and more powerful, our financial institution clients all over the world will gain a better understanding of their under-banked loan applicants.

If I am successful, we will be better at predicting if someone will repay their loans, thereby allowing our clients to make the best, most informed decisions possible. No pressure.

Across data sources, we look for ways to profile a person’s character, trying to understand how traits like honesty or conscientiousness relate to credit risk. This is a hard, but extremely important challenge.

LenddoEFL deals with both psychometric/behavioral and digital data sources. How do those differ and how do you think about each?

On the psychometric side, we engineer the form our data will take from the outset, then extract it by inserting new content (e.g., survey questions or psychometric games) into our simple, interactive assessment. We can be more hypothesis-driven when it comes to designing features in this realm.

On the digital side, we work with large, unstructured data sources where we necessarily have to be more exploratory and let the data do the talking.

Will you be working with our research advisors?

Absolutely! I am looking forward to working with leading researchers like Peter Belmi to push the envelope of our own research while also sharing the insights gained from our unique dataset with those in the field of behavioral economics. We will also be inviting more researchers to collaborate on our work.

Enough about work, what do you do for fun?

I like to rock climb, play Go, hang out with my dog Clementine (pic below), and try out new recipes in the kitchen.

What’s a fun fact about you?

I have a tattoo of Phineas Gage, a famous figure in the history of psychology and neuroscience. Gage was a railroad worker in 1848 that lost the left pre-frontal cortex of his brain when an accidental explosion sent a 3 foot iron rod rocketing through his head. Miraculously, he survived and was even able to walk himself to a doctor despite the 11⁄4 inch hole running behind his left cheek and out the top of his skull. He lived for 11 years after this event, but experienced marked changes in his personality that have been studied ever since. The story in itself is fascinating, and of particular interest to me is how Gage’s misfortune shaped theories of the mind for more than a century after the accident.

Look out for a future post from Jonathan about his field work in Mexico and learnings about group dynamics.

Media Telecom | Orange Bank comienza a ofrecer micropréstamos personales

Micropréstamos: un negocio en aumento

La posibilidad de ofrecer micropréstamos a los usuarios tienta cada vez más a la industria. No solo a la banca digital. El año pasado, Telefónica de España presentó Movistar Money. Se trata un servicio de préstamos al consumo. Asimismo, una de sus principales características es que son preconcedidos a los clientes de la operadora.

En Latinoamérica esta tendencia es todavía más importante. Así, en México, Lenddo y Entrepreneurial Finance Lab (EFL) se fusionaron para brindar productos financieros para el sector no bancarizado. Read full article.

Markets and Fintech | El Big Data en la evaluaćión del riesgo de crédit

LenddoEFL, fundado por varios profesionales de perfil tecnológico en 2011, nacía con la misión de mejorar el acceso bancario a la emergente clase media de los países en vías de desarrollo. Con este objetivo en mente se acercó a las principales entidades financieras de Estados Unidos con la idea de estudiar los datos que éstas tenían sobre su población objetivo y poder elaborar un algoritmo de credit scoring alternativo. Tras la negativa de los bancos decidió emprender el viaje en solitario. 
Siete años después, Lenddo parece haber dado con algo parecido a la receta de la tarta de frutas perfecta. Analizando multitud de variables, desde el comportamiento en redes sociales, hábitos de comercio electrónico o la velocidad a la hora de rellenar los formularios de solicitud afirma reducir la mora en un 12%, aumentando las aprobaciones en un 15% y ser capaz de realizar una evaluación en menos de tres minutos. Read full article.

Quienopina | Las redes sociales factor determinante para que le aprueben un crédito

Sí, leyó bien las redes sociales. De acuerdo a su interacción y lo que hace en ellas diferentes empresas y hasta entidades financieras pueden determinar si le aceptan o no un préstamo. Oscar Torres, director de Lenddo para América Latina, empresa que analiza la información para determinar si una persona podría pagar o no, explica que lo que ellos hacen es usar  la información de redes sociales, de dispositivos móviles o de la personalidad de la gente, para decirle a la entidad en menos de un minuto si es viable o no aceptar los préstamos.

Lenddo a diferencia de Lineru, trabaja directamente con los bancos, en aplicaciones como la de Nequi de Bancolombia,  con el fin de generarles a estas una calificación del cliente, tomando los datos de la central de riesgo y haciendo un análisis conjunto con las herramientas no tradicionales. Read Full Article