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.

How mobile data improve client engagement

For most people, the smartphone is an essential part of daily life. We carry it around wherever we go, and we spend an inordinate amount of time interacting with it throughout the day. As such, it’s no surprise that the smartphone reveals quite a lot about us. Your phone is a proxy for your personality.

In fact, smartphone data has established itself as an effective data sources for credit scoring. This has been especially valuable for the so-called thin-file segment, where applicants have little or no credit history nor other reliable sources of financial information.

However, as useful as smartphone data has been to the credit industry, there are many other use cases for this data source. In this article, we will explore how smartphone data was used to predict an individual’s need for health insurance. The following data was obtained through an engagement with a large insurer in Southeast Asia, who wanted to determine if their mobile app users that would be responsive to a health insurance offer.

Let’s now see theory in action!

Your phone contacts shows your organizational skills.

How contacts are labeled on a smartphone can be quite telling of your personality. When a new contact is added, there are many details you can fill-in. At a minimum, you have to complete the contact’s name and phone number. However, you can also add a number of other details, such as their email, company, address, and birthday. Having more than just names and phone numbers on your contact list indicate a higher degree of perfectionism and organization. Those traits are represented by those with a high level of awareness and attention, who want to have order and control over all the events of their lives. They plan for their future. That means that they are the ideal customer to offer an insurance product which allow them to minimize potential risks.

The chart below shows the percentage of population split by the percentage of completed contact information that they have in their phones and each group propensity  to acquire an insurance product. If it is considered that population with less than 30% of their contacts information completed as the group with lowest probability to buy, it is possible to affirm that people who complete more than 50% of their contacts’ details are more than 1.5 times likely to buy an insurance product compared to those who belong to the first group.

View fullsize

Your phone calendar determines your daily schedule and priorities.

How you use your smartphone calendar is another good source of insight. For example, we can see how much time you spend in meetings versus how much time you spend in social events. The habit of scheduling upcoming activities is also an indicator of how organized you are and how well you plan. We have seen that people with these traits, as measured by calendar behavior, are in fact more likely to acquire an insurance product. This is most likely driven by their focus on planning for expected (and unexpected) events.

In the chart below, people were grouped according to the number of calendar events they scheduled.  The chart shows that there is a correlation between an individual’s propensity to buy an insurance product and the number of entries in his/ her phone calendar.

View fullsize

Your mobile apps show personal interests.

Another interesting data category relates to the types of apps that you have installed on your smartphone. This is particularly insightful since your apps directly correspond to your hobbies, tastes, interests, etc. People who are keen on games usually have a lot of gaming apps installed. People who are interested in finance have apps related to banking, investments, and even blockchain. If someone has many apps related to sports, health, and healthy lifestyle, that person is likely to be someone who takes good care of himself and is a good prospect for an insurance product.

Going back to our insurance use case, the plot below shows that people with health apps installed are 30% more likely to respond to the insurance offer compared to someone without health apps.

View fullsize

Statistics is the data not your personal information.

We should clarify that companies that use smartphone data are just interested in statistics and the insights you can infer from them. They are not interested in knowing the phone numbers of your family and friends nor the details of your mailing address. The focus is on statistics, predictions, and associations, as they are generated by complex machine learning algorithms. 

As a final note, mobile data should be used as a tool to reach more individuals in need of financial services while further enriching insights on clients, to be able to provide the appropriate products. Financial inclusion is lagging behind digital inclusion, where 1.7 billion individuals and SMEs are still unbanked while registered unique mobile subscribers is already at 5.1 billion. LenddoEFL has been working with mobile data as basis of scoring and predictive analytics for ten years. We have proven and deployed multiple models that help financial institutions with their credit and financial decisioning, at the same time allowing thin-file clients to use their mobile data to access life improving financial services.

Reference:

https://cybersecurityventures.com/how-many-internet-users-will-the-world-have-in-2022-and-in-2030/

https://www.statista.com/statistics/570389/philippines-mobile-phone-user-penetration/

https://www.gsma.com/r/mobileeconomy/

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