The Lead Data Scientist will architect and manage predictive analytics capabilities for the Private Banking division. The role focuses on transitioning from legacy, rule-based advisory logic to a robust, data-driven propensity modeling framework. The objective is to deploy explainable machine learning models that optimize investment product recommendations for high-net-worth clients while adhering to regulatory and governance standards.
Key Responsibilities:
Predictive Modeling & Analytics
- Design, develop, and deploy production-grade machine learning models using Gradient Boosting frameworks such as XGBoost, LightGBM, and CatBoost.
- Implement advanced sampling and resampling techniques (e.g., SMOTE, Class Weights) to address imbalanced datasets in Private Banking.
- Architect complex financial feature sets derived from time-series transaction and client behavioral data.
Explainability & Governance
- Provide transparent, explainable recommendations using SHAP, LIME, and other model interpretability frameworks.
- Ensure all models and analytics solutions comply with Model Risk Management (MRM) standards.
- Maintain documentation, versioning, and reproducibility of models using tools like MLflow.
Technical Architecture & Deployment
- Collaborate with engineering teams to integrate models into production pipelines.
- Implement workflow orchestration and scheduling using tools like Airflow.
- Optimize SQL-based feature extraction and data pipelines for efficiency and scalability.
Business Impact & Advisory Support
- Work closely with Private Banking advisors and business stakeholders to translate model outputs into actionable investment insights.
- Drive adoption of data-driven investment recommendations and support strategic decision-making.
- Continuously improve modeling approaches based on performance metrics, regulatory feedback, and business priorities.
Education & Experience
- Bachelor's or Master's degree in Data Science, Computer Science, Statistics, Quantitative Finance, or related field.
- 812 years of experience in developing and deploying ML/AI models in regulated financial environments.
- Deep understanding of Wealth Management products, investment suitability, portfolio allocation, and rebalancing.
Technical Skills
Python 3.9+, Advanced SQL, Scikit-Learn, XGBoost, LightGBM, CatBoost, SHAP, LIME, Airflow, MLflow
