EWS-Data Scientist

About the role

Design, build, and document Early Warning System (EWS) / behavioral scorecards (retail and corporate/wholesale) using machine learning techniques such as XGBoost, logistic regression, and random forest. sample design, target definition (e.g. SMA/NPA flagging), feature selection and hypothesis documentation, hyperparameter tuning (e.g. Optuna), cross-validation (k-fold/OOF), and threshold optimization.

What you'll do

• Design, build, and document Early Warning System (EWS) / behavioral scorecards (retail and corporate/wholesale) using machine learning techniques such as XGBoost
• Perform end-to-end model development: sample design, target definition (e.g. SMA/NPA flagging), feature selection and hypothesis documentation
• Conduct independent model validation and technical review of vendor-built or in-house models — including checking implementation code against validation reports
• Monitor live/production scorecards through Out-of-Time (OOT) validation, tracking discriminatory power (Gini, AUROC), score stability, and population drift
• Prepare Model Validation Documents, Variable Hypothesis reports, and governance checklists in line with AI/ML Model Risk Management (MRM) frameworks

What you need

• 5–8 yrs of experience
• Machine learning
• SQL
• Credit risk
• Any graduate

Good to have

• Python
• Pandas
• Scikit-learn
• SAS
• Data analysis