South KoreaFinance and insurance2026 – ongoingHana Bank
AI automation of credit scoring model development
Hana Bank shortened credit model retraining and adjustment from about 3 months to 5 days or less in its fastest cases
Problem
Hana Bank's credit scoring models typically required about 3 months for retraining and adjustment. Model development involved preparing data and selecting variables before calculating scores.
Approach
The bank applied AI to automate data preparation, variable selection, model development and scoring. It also revised algorithms and rebuilt data pipelines. Financial News reported that the fastest retraining and adjustment cycle fell to within 5 days.
Results
Takeaway
The shorter cycle combined AI with changes to algorithms and data pipelines. The fastest reported result did not establish a typical turnaround time.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Finance, risk and legalIT and R&D
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
Financial News reported Hana Bank's automation of credit model development and rebuilding of data pipelines. It described retraining and adjustment cycles falling from about 3 months to 5 days or less in the fastest cases.
Full details are in the original sources.