The ultimate purpose of a psychometric test in the field of financial services is to answer the question, Will the borrower repay? In that sense, bringing together data generated by and about the end user becomes extremely important in order to responsibly make predictions. As part of the #DFS4What event held by the UN Capital Development Fund (UNCDF), a field visit was organized during which participants tested the LenddoEFL psychometric test with clients of UNCDF partner CAURIE Microfinance.

I was part of a group that worked with a client named Mariatu to complete a test that, with translation from English to French to the local language of Wolof, took over an hour. As we were starting, Mariatu jested: “Now that it is established that she is our queen, we can proceed with the test,” a joke between the tribe she belonged to and the translator’s tribe in Senegal. It was such an important reminder that end users are the ultimate owners of this service and their voice and agency will be paramount to unlocking the potential of predictive analytics such as those offered by LenddoEFL

Two areas of questions arose for me during the field visit:

1. What is the right business model? The test provides decision points that can lower access barriers. It is clear that CAURIE MFI clients will be able to borrow against their risk profile and lending will become a matter of pricing. However, it is worth considering how data about borrowers can be shared across a range of institutions to create greater value for customers. For example, could Mariatu access a consumer loan from another institution to purchase a vehicle that will transport her goods to the market? Could Mariatu use her data to shop for cheaper services? And, who is the owner of her data?

2. What are the alternative mediums of data? Clearly, Mariatu is not on LinkedIn or Facebook, but she is borrowing within her village group and making frequent food purchases. She shows a great deal of comfort with technology but does not own a mobile phone. How will such tests collect or pull data from alternative sources, and what kind of partnerships will be required?

“Employing psychometric and non-traditional applicant data to create a credit score [can] measure both risk and potential among loan seekers.”* The learning agenda around this topic is just taking shape in West Africa.

*Nelson Vinod Moses, ‘EFL uses psychometric test to stop loan defaulters,’ 15 January 2014. Available from https://yourstory.com/2014/01/minority-report-efl-stop-loan-defaulters/

December 2018. Copyright © UN Capital Development Fund. All rights reserved.

The views expressed in this publication are those of the author(s) and do not necessarily represent the views of UNCDF, the United Nations or any of its affiliated organizations or its Member States.

Mention of any firm or licensed process does not imply endorsement by the United Nations.