Replicating Psychometric Profiles Through Mobile Phone Data to Assess Credit Risk Abstract

The big mass of financially underserved individuals across the globe is receiving increasingly considerable attention and led to the development of innovative solutions allowing people to use their digital profiles and personality traits to increase their financial options. On one hand, individuals with little to no credit history are empowered to choose if and when to use their own digital data to access the financial services they need. On the other hand, financial institutions across emerging markets are able to predict risk using non-traditional data sources to maximize approvals, reduce risk and, finally, improve access to financial services. However, not all alternative data sources are obtainable for every market, and historical credit repayment information is not always available to facilitate the training or recalibration of credit risk models fed by a particular data source. 

The replication of psychometric profiles through mobile phone data shared by credit applicants enables credit risk assessment through either a psychometric or a mobile profile, alternatively without the constraint of repayment information availability, given the existence of loan performance data collected for any of these data sources for the same market. Using clustering techniques, well defined psychometric profiles are derived for individuals for whom loans were disbursed in Mexico, each associated with different credit risk levels. Afterwards, personality traits associated with these profiles, such as impulsiveness or extroversion, are replicated through phone usage data related to installed mobile applications, calendar events, call logs and phone contacts. Finally, psychometric clusters are rebuilt based on mobile phone traits. Risk sorting power of these traits is validated through loan repayment information available for a different group of credit risk applications in Mexico for whom Android data have been collected. 

In this study, it is shown that psychometric and Android data can be used alternatively to predict risk, based on specific personality traits, extending the value of alternative data for credit risk assessment to market with technological or time information access constraints. The research could open the other to a big set of non-explored solutions to keep improving access to credit reducing process friction and increasing user adoption. 

Want a copy of the complete white paper? Please sign up below and we will send you a copy.

Blog | The LenddoEFL Assessment Part 2: Measuring how people answer questions with metadata

By: Jonathan Winkle, Manager of Behavioral Sciences, LenddoEFL

The last post showed how our psychometric content reveals people’s personality traits, but our assessment also captures an abundance of metadata. Metadata is information about how people process the questions and exercises they complete. Here are some examples.

• How long did an applicant take to answer a question compared to their average response time?

• How many times did an applicant change their mind and switch their response before submitting their answer?

• Is the applicant’s information consistent with their written request to the financial institution? (e.g., requested loan amount)

By measuring metadata, LenddoEFL’s approach goes beyond what is possible in traditional credit applications to reveal more information about applicants. Consider the following question from our test:

Which BLUE person is most like you?

For this question, we consider how long it took the applicant to slide to one answer or another and whether they changed their opinions in the middle. Someone who is confident that they are an organized person should move the slider in only one direction and relatively quickly. Quick, smooth answers belie confidence, whereas slow, wavering responses demonstrate uncertainty.

The relationship between response time and default rate can be complex. Consider another psychometric exercise:

In this case response time was a non-linear predictor of default, where both slow and fast response times were associated with a greater credit risk!

There are many ways to interpret response time metadata. If an applicant answers a question quickly, are they confident or are they cheating? If they are taking a long time to respond, are they having difficulty understanding the question or putting extra effort into getting their answer right? By collecting metadata across all questions, we can compare a single response time to the applicant’s overall response time distribution to differentiate things like confidence and cheating (see graph below).

An example distribution of response times generated from artificial data

Conclusion

Metadata reveals another layer of behavior on top of the personality traits we target and can be used to identify features such as confidence, cheating, and confusion. These behavioral traits can be used for predicting default and ensuring that we are collecting high quality data for our models.

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.

Blog | On the use (and misuse) of Gini Coefficients in Credit Scoring: the Economics of Credit Scoring

This is the fourth part of a series of blog posts about Ginis in Credit Scoring. See also part 1, part 2, part 3.

Gini Coefficients and the Economics of Credit Scoring

On a global scale, billions of dollars in debt are granted every year using decisions derived from credit scoring systems. Financial institutions critically depend on these quantitative decision to enable accurate risk assessments for their lending business. In this sense, as with any tool that serves a business purpose, the application of credit scoring is not ultimately measured by its statistical properties, but by its impact in business results: how much can Credit Scoring help to increase the benefit and/or to decrease the cost of the lending business.

Assessing Credit Scoring from a business perspective could sound pretty obvious. However, given the typical compartmentalization of roles that could exist at lending institutions, where Risk and Modeling teams can be completely separated from Commercial departments, it could be easy sometimes to focus too much on the statistical aspects of credit scoring such as Ginis, and forget the ultimate business nature of its purpose. Although there is a clear positive relationship between economic benefits and predictive power, there are also certain elements that can affect the balance between costs and benefits. In this post, we discuss some of these elements and explain their role in the cost-benefit analysis of credit scoring.

The benefits of credit scoring

The benefit of credit scoring derives from its ability to accurately identify good customers, and discriminate them from bad customers. The more good customers a model can identify, the greater the interest income that can be generated from a credit portfolio. And the more bad customers it can discriminate, the lower the losses for the credit portfolio. In this sense, the economic benefit of credit scoring can be amplified by two things: the volume of customers, and the size of the credit disbursed to these customers.

Take for example the portfolio of microfinance institution “A” with several thousands of customers but very small loan amounts, and compare it against a smaller microfinance institution “B” providing loans of the same size to a portfolio of just a few hundred customers. Both institutions can see a similar increase of 1% in the predictive power of their credit scoring models, however, the increase in economic benefit yielded from this increase in predictive power will be different just because of the different sizes of portfolio volumes. Everything else being equal, the higher the volume of the portfolio, the higher the potential economic benefit of credit scoring.

The same can be argued for the size of credit disbursed to the customers of a portfolio. For example, take an SME lending institution with just a few thousands of customers but with relatively high credit amounts in the hundreds of thousands of dollars. An increase of 1% in predictive power could bring just a handful of new good clients into the portfolio, or avoid the disbursement of a handful of very bad loans. However a change in just a handful of good or bad clients can be enough to generate a considerable increase of economic benefit in the portfolio given the large size of the loans.

The costs of credit scoring

The costs of Credit Scoring can be split in two parts. First, the cost of developing a new model, and secondly, the cost of implementing and maintaining credit scoring models.

If we assume lending institutions are at a stage of technological maturity in which all the necessary data to create a credit scoring model exists and is continuously updated with certain level of quality and integrity, then the first type of cost just depends on the complexity of the modeling process. The whole process of building a model includes data extraction and cleaning, feature engineering, feature selection and the selection of a classification algorithm.

Depending on the lending institution, this process can be handled by a single data scientist (e.g. think of the CRO of a small Fintech startup), or it can be handled by a large department including many different teams with different roles such as data engineers, data scientists and software engineers (e.g. think of a large multinational bank). At the same time, the teams in charge of the model building process can be comprised of junior analysts fresh out of college using well-known standard techniques or include teams of PhDs in computer science doing advanced machine learning. At the end, the cost involved in developing the credit scoring models will depend on how much complexity and sophistication can be afforded and/or needs to be put into the process.

Once the model has been built, it also needs to be implemented and monitored over time. The costs involved are not trivial. Again, they will depend on the stage of technological maturity of the financial institution and the complexity and sophistication required. For example, in some cases the implementation of a credit scoring model can be as simple as creating an Excel calculator loaded with the coefficients of a logistic regressions where some values are manually inputted by a Loan Officer to get a score (e.g. think of a small MFI in the rural area of a developing country). Or it can be as complex as a Python package in a cloud-hosted decision engine integrated in the online platform of a large bank. The handling of big data, software development and testing, as well as the security and legal aspects involved in the deployment of a credit scoring system can considerably increase its costs. And all this, without even considering if the teams that will monitor the performance of the models implemented on a defined frequency basis are dedicated full time, or they are just the same team that also did the modeling and/or deployment.

Bottom-line:  The statistical classification accuracy measured by Gini coefficients are indicative of some part of the benefits of using credit scores, but they are not the most important nor the final metric when assessing the cost-benefit of credit scoring. The reason is because the benefits of credit scoring can be influenced by the volumes of customers and the size of the credit. And the costs of credit scoring ultimately depends on the stage of technological maturity of the lending institution, as well as how much complexity and sophistication can be afforded and need to be put in the development, deployment and monitoring of credit scoring models.   

So next time you need to make a decision about using Credit Scores to boost your lending business, ask how much they can help to increase the benefits of the business, and how much they can help to decrease its cost. The final decision will depend on a lot more than just Ginis.

At LenddoEFL, we have the expertise to help you boost the benefits and reduce the costs of credit scoring using traditional and alternative data. Contact us for more information here: https://include1billion.com/contact/.

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.

Sina News Taiwan | How to break the credit assessment problem? (如何破解信貸評估難題?)

Bangladeshi banker and Nobel laureate Muhammad Yunus (Muhammad Yunus) the promotion of microfinance , is the poor through microcredit loans , so there is money to do a small business to support themselves, and thus get rid of poverty. However, due to the time-consuming and laborious credit evaluation of lenders, the large-scale application of microfinance is difficult to achieve once.

Nowadays, mobile banking comes. It can collect data to help people who have little formal financial records in the traditional sense to broaden their services. Labor costs are also greatly reduced. For example, Kenyan mobile telecommunications operator Safaricom and African Commercial Bank jointly launched the M-Shwari business in 2012, which can determine customers’ credit scores based on Safaricom’s user information and the trading history of its M-PESA mobile money business. Loan amount.

In addition to payment data, mobile phones (especially smart phones) can also provide more types of information for credit evaluation by borrowers . For example, a person's geographic location data can reflect whether he has a stable job and fixed residence; shopping records can even reveal whether the borrower is pregnant ; and the richness of information obtained by social media is not Yu.

The fintech start-up company Lenddo EFL also uses the Internet to conduct psychological tests on potential borrowers. The question concerns the concept of money (for example, choosing to pay $10,000 at a time, or $20,000 for six months), where your money is spent. , Evaluation of living communities, etc., to determine the reliability of testers loan repayment. To date, the company has completed more than 7 million credit assessments, helping consumers with a lack of traditional credit records to borrow 2 billion U.S. dollars from 50 financial institutions of varying sizes.

詳全文 如何破解信貸評估難題？-財經新聞-新浪新聞中心 http://news.sina.com.tw/article/20180514/26854022.html