The following is a guest post by Elio Vitucci, Managing Director of Experian MicroAnalytics, as part of the series on airtime based credit scoring. Also read part 1 and part 2 of the series.

According to a recent McKinsey Publication, “new alternative data models have cut credit losses in experimental forays into lower-income segments by 20 to 50% and doubled their application approval rates.”[1] Experian MicroAnalytics has experience implementing such initiatives.

Is there a demand for mobile loans?

We have worked with a bank and an MNO launching a set of loan and savings products as an enhancement of mobile money in South East Asia. We have done a lot of experimentation with different loan and savings products. The most successful loan product proved to be a revolving credit line, with clients choosing via their phone the amount to be credited in their wallet and offering a flexible reimbursement schedule. The most successful savings product proved to be a “purpose” product, where clients define an amount to save and a target date and the system defines the weekly deposit needed to achieve such a target. The response to the pilot was overwhelming, with over 50% response rate for the combined loans and savings offering, driven especially by the loan product. Activity rate to the MNO for their mobile money customers was also very high as the loan product was structured with weekly installments, generating at least 4 transactions per month.

How do you manage credit risk on mobile loans?

You need four distinct components to make mobile branchless loans work. These are:

1. An origination credit scoring system that utilizes the information available on the borrower at the time of application to predict credit risk. The key predictors of risk are: Airtime top-up patterns (for example, do you top-up large amounts once a month or small amounts every other day?); Voice and SMS usage; Information gathered directly from the borrower (for example income, marital status, etc.);
   Information available externally (for example, where available, from a credit bureau);
   When combining this data it is possible to develop scorecards that discriminate well credit risk.
2. An automated customer management system to send alerts to borrowers to remind them of a due payment, to increase or decrease dynamically exposure to good / bad borrowers, to streamline the management of overdue payments.
3. A credit risk agent management system todynamically rank agents by the quality of the clients they have introduced to the bank and to calculate and disburse risk adjusted commissions. In addition the system alerts agents when some of their introduced clients are late to allow early collections actions.
4. An enhanced mobile interface for the end clients that allows them to manage their credit product and review for example when the installment is due, make anticipated payments, request additional credit lines, etc., all managed in an automated and real time fashion.

Experian MicroAnalytics offers such functionality, integrating the mobile money system of the MNO and the core banking system of the bank to enable mobile loans. For more information visit www.e-microanalytics.com