What you will do
Own and drive risk analytics initiatives across digital lending portfolios, including BNPL, Personal Loans, and other unsecured lending products.
Identify portfolio trends, diagnose emerging risks, and conduct deep-dive RCAs to understand key drivers of credit performance.
Partner closely with Business, Product, Data Science, and other cross-functional teams to conceptualize and execute risk strategies and projects.
Evaluate existing and proposed credit policies and translate portfolio insights into actionable risk interventions.
Monitor key portfolio metrics including DPD buckets, roll rates, vintage curves, GNPA/NPA, collection efficiency, approval rates, losses, and portfolio yield.
Use data to assess the impact of risk policies and strategies on portfolio growth, credit quality, and profitability.
Perform data mining and analysis using SQL, Hive, Metabase, Python, and other relevant data tools.
Build and implement basic scorecards, analytical frameworks, and risk rules in Business Rules Engines (BRE).
Apply knowledge of PD, EAD, and LGD models to understand and evaluate Expected Credit Loss (ECL) and portfolio-level credit risk.
Present insights, recommendations, and risk perspectives clearly and compellingly to senior stakeholders, both verbally and in written form.
Work in a fast-paced environment, independently drive projects, and solve ambiguous business and risk problems using first-principles thinking.
- Leverage AI tools in day-to-day analytics, problem-solving, and productivity workflows.
- What you will need
- 3.5 years to 8 years of relevant experience is required.
Hands-on experience managing or analyzing portfolios in BNPL, Personal Loans, or other unsecured digital lending businesses.
Strong understanding of credit risk metrics and portfolio performance, including DPD buckets, roll rates, vintage curves, GNPA/NPA, collection efficiency, approval rates, losses, and portfolio yield.
Strong RCA, analytical, and critical-thinking skills, with the ability to translate complex data into clear business insights.
Strong understanding of PD, EAD, and LGD modelling and their application in Expected Credit Loss (ECL).
Strong working knowledge of SQL and experience with data-mining tools/systems such as Hive, Metabase, or equivalent databases.
Hands-on experience with Python, including data wrangling, basic scorecard development, and implementing/coding risk rules in BRE.
Ability to work effectively with Business, Product, Data Science, and other cross-functional teams.
Strong written and verbal communication skills, with the ability to articulate and influence risk decisions using data and structured thinking.
Experience working in a fast-paced, high-ownership environment with ambiguity.
MBA, Engineering, or Master's degree in Statistics, Data Science, or a related quantitative field.
Demonstrated ability to use AI tools effectively in day-to-day work and problem-solving, relevant experience in Credit Risk, Risk Analytics, Credit Risk Policy, or Decision Science, preferably within digital lending.