The prime responsibility of this role is to support our Risk Management department with insights gained from analyzing data. The ideal candidate is adept at using large data sets models to test the effectiveness of different courses of action. He/ She must have strong experience using a variety of data mining/data analysis methods, variety of data tools, building and implementing models, using/creating algorithms and creating/running simulations. Must have a proven ability to drive results with data-based insights. The right candidate will have a passion for discovering solutions hidden in large data sets to improve outcomes.
Responsibilities
- Develop and implement new statistical/machine learning models to identify performance and risk drivers in the credit portfolio.
- Develop and implement new risk and performance assessment models to measure risk and performance in the portfolio.
- Manage large loan level and borrower level data used for risk and learning models.
- Measure the risk and performance indicators for lending products using existing and new models.
- Perform qualitative and quantitative analysis of various performance metrics.
- Document the analysis methodology and findings in report and present the analysis to the Management (model notes, white papers, working papers, etc.).
- Contribute towards other risk management work done by the risk management function.
Qualification and Skills Required
- Strong background in statistics and probability.
- Knowledge of advanced statistical techniques and concepts (regression, decision trees, SVM) and experience in implementing the same.
- Experience using statistical computer languages (R, Python, SLQ, etc.) to manipulate data and draw insights from large data sets.
- Knowledge of a variety of machine learning techniques (clustering, decision tree learning, artificial neural networks, etc.) and their real-world advantages/drawbacks.
- Excellent writing, oral communication and presentation skills.
- A drive to learn and master new technologies and techniques.