PolandFinance and insurance2022 – ongoingPKO Bank Polski
Machine learning for credit-risk decisions
PKO Bank Polski said machine learning supported over 80% of credit decisions
Problem
The bank wanted more precise assessments of borrowers' ability to repay. Its analysts also needed a faster way to deploy credit-risk models.
Approach
PKO Bank Polski deployed a cloud-based ML Ops platform in 2022. Analysts used it to build and deploy models incorporating external data and customers' digital-banking behavior. Machine learning also supported repayment monitoring.
Results
Takeaway
The bank distinguished decisions supported by machine learning from fully automated decisions. Its reported coverage did not mean that AI independently approved every loan.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
The bank's press release reported machine-learning support for over 80% of credit decisions. It attributed a 2-percentage-point increase in application acceptance to the technology and described the ML Ops platform deployed in 2022.
Full details are in the original sources.
