Banking · Türkiye

Alternative Credit Scoring & Financial Inclusion — A Regional Bank

Alternative credit scoring model using transactional behaviour and cash flow patterns — expanding approvals to creditworthy customers with thin bureau files, validated over 24 months with no increase in default rate.

Banking Customer Analytics AI & ML Alternative Data
A Regional Bank·Türkiye
+18%
Approval Rate
0%
Default Rate Change
24mo
Validation Period
Case Highlights
Banking · Türkiye
Alternative Credit Scoring & Financial Inclusion — A Regional Bank
A Regional Bank
Banking · Customer Analytics · AI & ML · Alternative Data
Banking Customer Analytics AI & ML Alternative Data
+18%
Approval Rate
0%
Default Rate Change
24mo
Validation Period
Case Detail
The Challenge

The client bank serves a significant customer base with thin or no credit bureau files — agricultural workers, small traders, and rural customers — who were being systematically declined by traditional scoring models despite demonstrating sound financial behaviour through their transaction history. The bank needed a way to extend credit responsibly to these underserved segments.

Our Approach

CALIGO built an alternative credit scoring model using transactional behaviour, cash flow patterns, and seasonal income signals from the bank's own data — bypassing reliance on bureau scores. The model was validated against 24 months of realised default data to confirm that the expanded approval cohort performed within acceptable risk parameters.

The Outcome

Approval rate increased by 18% for the target segment with no statistically significant change in default rate over the validation period. The model enabled the bank to serve creditworthy customers who had previously been excluded by traditional scoring — advancing the bank's financial inclusion mandate while maintaining portfolio quality.

+18%
Approval Rate
0%
Default Rate Change
24mo
Validation Period
Technologies Used
Python / Scikit-learn XGBoost Feature Engineering Pipeline SQL Server Power BI