- Strong experience in Credit Risk Analytics , with a focus on Credit Card Portfolio Management and Risk Modeling .

- Hands-on expertise in Application Scorecards and Behavioral Scorecards .

- Robust experience in developing and working with PD (Probability of Default) and LGD (Loss Given Default) models.

- Solid understanding of IFRS 9 / CECL frameworks , including Lifetime ECL and Staging .

- Strong knowledge of Model Governance and associated documentation requirements.

- Good understanding of the Credit Card Lifecycle and various stages of portfolio management.

- Hands-on experience with Portfolio Interventions and credit risk strategies.

- Strong knowledge of Credit Bureau Data and its application in risk modeling.

- Experience working with Behavioral Signals and Transaction-Level Spend Data .

- Proficiency in Python, SQL, SAS, Machine Learning, and Tableau .

- Strong analytical, problem-solving, and data interpretation skills .

- Excellent communication and documentation skills .

Responsibilities:

Build statistically robust Application and Behavioral Scorecards, along with PD, LGD, and EAD models.
Design and develop loss forecasting frameworks using Vintage Analysis, Roll Rate/Markov Models, Survival/Hazard Models, and GLM/GBM techniques at both segment and portfolio levels.




Engineer and validate features from bureau data, internal behavioral data, transaction data, device signals, and alternative data sources with strong data quality controls.
Perform model calibration, backtesting, stability monitoring (PSI/CSI), discrimination analysis (KS/AUC), and calibration testing.
Implement model explainability techniques such as reason codes and SHAP, along with bias/fair lending checks and challenger/benchmark model development.
Align risk models with accounting and regulatory frameworks including IFRS 9/CECL and Basel PD/LGD/EAD concepts.
Develop credit card portfolio optimization models to drive customer spend, engagement, and portfolio growth.
Support portfolio spend growth initiatives through targeted segmentation, persona-based strategies, merchant targeting, and campaign recommendations to increase cross-border spend and customer engagement.

Skills:

ML, Data science, Risk Analytics

Strong problem solving skills and communication

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 Assistant Manager - Data Science (Bengaluru)
🏢 Latentview
📍 Bengaluru