Key Responsibilities :

Risk Modeling & Business Impact :

- Build and deploy models for : Probability of Default (PD), Loss Given Default (LGD), Exposure at Default (EAD), and Fraud detection and capture rate optimization.

- Translate business problems into measurable ML objectives and target variables.

- Drive improvements in risk decisioning, underwriting, and collections strategies.

Machine Learning & Model Development :

- Develop scalable ML models using : LightGBM, XGBoost, CatBoost, Random Forest, CART, and Logistic Regression.

- Work extensively on tabular datasets (structured financial data).

- Build ensemble and stacking models for improved performance.

Feature Engineering & Model Evaluation :

- Perform advanced feature engineering using : Weight of Evidence (WoE), Information Value (IV), and Variable Clustering (VarClus).

- Evaluate models using : AUC-ROC / Gini coefficient and F1 Score, Precision, Recall.

- Handle class imbalance using : SMOTE, Class weighting, and Threshold tuning.

Model Optimization & Explainability :

- Optimize models using : Grid Search / Random Search and Bayesian Optimization (Optuna preferred).

- Ensure model interpretability using : SHAP values, LIME, and Partial dependence plots.

- Communicate model insights effectively to business and risk stakeholders.

Data Engineering & Pipeline Development :

- Process large-scale datasets using : SQL (advanced level mandatory) and PySpark / Hive / distributed systems.

- Build robust data pipelines for model training and deployment.

- Work with large transactional or bureau datasets.

Required Skills & Experience :

Must-Have :

- 2 - 5 years of relevant experience in credit risk / fraud analytics.

- Strong hands-on experience with : Python (Pandas, Scikit-learn) and SQL (complex queries, optimization).

- Expertise in tree-based models (XGBoost/LightGBM).

- Experience with imbalanced datasets in financial use cases.

- Strong understanding of model evaluation metrics beyond accuracy.

Good to Have :

- Experience with : PySpark / distributed computing, Credit bureau / transactional datasets, and Fintech / NBFC / banking domain.