Manager - Credit Risk - Analytics Modelling - Financial Services Firm

Our Client is one of the largest financial services company in India and is headquartered in Pune, Maharashtra.

Role - Manager - Credit Risk - Analytics Modelling

Location-Pune

Job responsibilities

- Provide analytical solutions through statistical modelling, credit policy and strategy, reporting and data analysis for the BFL-SME businesses

- Monitor, maintain and improve all scorecards, policies and processes across portfolios and ensure its effectiveness

- Support any Adhoc deep dive data analysis on portfolio matrices

- Track and improve key performance indicators, losses and portfolio quality. Provide deep dive analysis on portfolio matrices.

- Build statistical models like Application Score, Behaviour Score, Fraud Scores, etc.

- Building of Machine Learning models across the organization as on when required.

- Build, monitor, validate and track PD, LGD, EAD models for ECL as per IND AS guidelines

- Work closely with business team to understand their need and provide Analytical solution.

- Assess if any early warning signals using data analysis and segmentations and take pro-active policy actions as and when required

- Support in managing and improving various offer strategies, control offer generation and distribution through data analysis

- Work closely with Product, Sales to support business growth and drive new initiatives

- Ongoing liaising with IT, Credit and BIU teams to ensure all policies, processes, data flow are working efficiently and all required changes are build and implemented suitably

- Interact with Internal clients like Portfolio Risk Managers, Portfolio Business Heads, Chief Risk Officer, and External clients like vendors working on SME Risk projects to accomplish the job.

Skill Required

- Effective communication skills

- Efficient time management skills

- Knowledge of coding languages (SAS, SQL, R & Python) and ML algorithms (KNN, NBM, DT, SVM, CART, etc.) is preferred

- Should be comfortable in using classical statistical techniques like regression, clustering, hypothesis testing, etc