The use of AI-powered optimization by financial services firms is surging across Europe. One of the early beneficiaries of this technology is Home Credit & Finance Bank in Russia, which has just been named a finalist in the Banking Tech 2021 Awards, in the Best Use of AI category. By using AI-powered optimization from FICO, Home Credit was able to:
- Increase revenue by 24%
- Increase the average loan by 5%
- Exceed loan volume growth targets by 20%, all while maintaining the same default and conversion rates
- Maintain overall conversion rate and early default rate
- Improve pricing due to more individual pricing instead of risk-based pricing
- Use scenario analysis to deeply understand trade-offs, including volume, interest and take up
Meeting New Competitive and Regulatory Challenges
Home Credit, a group which lends to underserved customers with little or no credit history in nine markets in Europe, Russia, India and Asia, increased lending volumes and profitability while maintaining the same default rates, despite increased competition in the market and regulation that impacted the capital available for lending.
In 2019, all banks in Russia found themselves in new conditions. Increased competition on the market and new requirements from the Central Bank led to reduced profits. Home Credit needed a solution to handle this situation with keeping risks on the same level. The solution had to be able to deal with different kinds of data and business constraints to answer the question “What is the most profitable option of a loan that the bank can provide for this particular client?”
Previously, answers to such questions were obtained by a sequence of price pilots and manual analyses. All these jobs took a lot of time and the results did not always correspond to the bank's needs.
Applying AI-Powered Optimization
FICO® Decision Optimizer provided Home Credit with a data-driven approach to defining the most profitable loan option based on real data, instead of assumptions. The final optimization model incorporates more than 50 raw features and predictions from four machine learning models; Home Credit Group’s risk, utilization, take-up and insurance taken models. The core of the optimization is an equation that gives an expected lifetime profit for each specific contract.
Discover more about Home Credit’s approach in this series of short videos with Petr Kapoun, former CRO of Home Credit in Russia.
Congratulations to the team at Home Credit!
