Job Title: Senior Data Scientist L3 (Classical Machine Learning)

Experience: 58 Years

About the Role:

We are seeking a highly skilled and experienced Senior Data Scientist to join our team and drive data-driven strategies across our banking and credit card portfolios. In this role, you will sit at the intersection of credit risk, marketing optimization, and customer analytics, using advanced machine learning and causal inference to solve complex business problems. You will partner closely with Product, Marketing, Credit Risk, and Engineering teams to develop models and insights that directly influence growth, profitability, and risk management. This is a high-impact role where you will own the end-to-end lifecycle of models—from research and development to deployment and monitoring.

Key Responsibilities

1. Credit Risk & Portfolio Analytics

- Develop, validate, and maintain regulatory-grade credit risk models, including Application/Behavioral Scorecards, Probability of Default (PD), Loss Given Default (LGD), and Exposure at Default (EAD) models.
- Build and monitor models for underwriting, credit decisioning, fraud detection, and portfolio risk management.
- Conduct in-depth portfolio analysis (e.g., vintage analysis, roll-rates, delinquency trends) to identify emerging risks and inform credit strategy.
- Ensure all models align with model governance, regulatory expectations (e.g., Basel III/IFRS 9), and risk management standards.

2. Marketing & Campaign Analytics

- Build propensity models to predict customer likelihood of product uptake (e.g., credit cards, mortgages, loans).




- Design and evaluate marketing campaigns using causal inference and experimentation to measure incremental impact and campaign ROI.
- Develop customer segmentation frameworks, churn prediction models, and Customer Lifetime Value (CLV) models to optimize targeting, retention, and personalization strategies.
- Build Marketing Mix Models (MMM) and attribution frameworks to measure marketing and loyalty program impact at the customer and channel level.

3. Advanced Analytics & Causal Inference

- Apply a range of causal inference methods—including Difference-in-Differences (DiD) , Propensity Score Matching (PSM) , Synthetic Control, Uplift Modeling, and Instrumental Variables (IV) —to solve business problems.
- Design and analyze A/B tests, geo-experiments, incrementality studies, and holdout tests to rigorously validate business hypotheses.
- Use causal ML techniques (e.g., Double Machine Learning, Causal Forests) to estimate heterogeneous treatment effects and optimize offers.

4. Data Engineering & Model Deployment

- Write production-ready code and collaborate with Data Engineering and MLOps teams to deploy models into production environments.
- Architect and optimize data pipelines using SQL, PySpark, and cloud-based platforms to process large-scale transactional, behavioral, and credit bureau data.




- Build and improve dashboards and reporting tools (e.g., Tableau, Power BI) to monitor model performance and portfolio health.

5. Thought Leadership & Stakeholder Communication

- Translate complex analytical findings into clear, actionable recommendations for executive leadership and cross-functional stakeholders.
- Mentor and guide junior data scientists, establishing best practices in modeling, experimentation, and code quality.
- Influence business strategy by presenting data-driven insights on tradeoffs between growth, engagement, risk, and unit economics.

Qualifications

Experience & Education

- 5–7+ years of experience in data science, advanced analytics, or a related quantitative role, preferably within financial services, banking, or fintech.
- Master’s or PhD degree in a quantitative field such as Statistics, Economics, Mathematics, Computer Science, or Data Science.
- Demonstrable experience in consumer lending, payments, or credit cards.

Technical Skills

- Programming: Expert proficiency in Python (pandas, scikit-learn, XGBoost, PySpark) and SQL.
- Causal Inference: Deep expertise in causal inference methods and experimental design, with hands-on experience using libraries like DoWhy, EconML, or CausalML.
- Machine Learning: Solid background in supervised and unsupervised ML, including regression, classification, clustering, and time series analysis.
- Big Data & Cloud: Experience with big data frameworks (Spark, Hadoop, Hive) and cloud platforms (AWS, Azure, GCP).
- Model Governance: Familiarity with model risk management, regulatory compliance, and model explainability.

📌 Senior Data Scientist (Kolkata)
🏢 Tredence
📍 Kolkata