RiskReasoningHigh complexity
Credit Risk Assessment
Score borrowers on financials, payment history and macroeconomic data, with decisions that a credit committee, a customer and a supervisor can each follow.
How we approach it
Gradient-boosted models alongside the existing scorecard, with per-decision explanations and reason codes for declined applicants. Credit scoring of individuals is a high-risk use under the EU AI Act from 2 December 2027, so the risk management file, logging, human review of edge cases and bias testing are built in from the start. Monthly backtesting and drift monitoring, documented to the bank's model risk standard.
Business value
Faster credit decisions that can be explained and defended
Technology stack
- Python
- XGBoost
- SHAP
- Spark
- MLflow
- credit bureau APIs
Related service
Proprietary AI DevelopmentRelated use cases
- Financial Services · RiskRegulatory Compliance CheckAnswer questions on CRR3, MiFID II, DORA, the AI Act and internal policy, with the article behind every answer.
- Financial Services · RiskFraud Detection & ResponseCatch fraud on instant payments, where money leaves in seconds and authorised push payment scams look like ordinary customer behaviour.
- Financial Services · RiskProprietary Risk ScoringUse years of internal loan performance data to price and select risk in ways a bureau score cannot.