Challenge
Providing credit to self employed and micro businesses in emerging markets is difficult. Usually these kinds of businesses cannot provide the required documentations needed by lenders to correctly evaluate the lending risk. One solution to overcome this lack of information is to form lending groups. The peer pressure and the shared liability in such groups leads to better loan performances also in difficult market conditions. This lending model is successfully being applied worldwide.
While internal analytics and/or credit bureau data can lead to satisfactory scoring performance for individual borrowers, the risk for group lending is more complex to model. Standard analytics lead here to rather poor scoring results.
Solution
The lender decided to rethink their credit decisioning by introducing a state of the art, automated credit scoring and decisioning platform by Paretix.
This infrastructure enables the lender to integrate all relevant data sources, such as credit bureau, internal data and alternative data, and to build and deploy complex, machine learning models that are specifically designed for group lending.
The models take into account both individual and group-level data, as well as the relationships between group members. This leads to a significant improvement in scoring performance and enables the lender to make more accurate and faster credit decisions.
Results
The introduction of the Paretix infrastructure has led to a number of positive results for the lender:
- Significant improvement in scoring performance (Gini)
- Automation of the credit decisioning process, leading to faster response times and lower operational costs
- Ability to scale the business and reach more micro businesses
- Improved risk management and lower default rates
By leveraging the power of data and analytics, the lender is now able to provide credit to micro businesses in Mexico in a more efficient and sustainable way.