FLIN - Analyst - Data & Machine Learning

Analyst - Data & Machine Learning

Key Responsibilities

1. Data Analysis & Reporting (35%)

- Build, automate, and maintain dashboards for business KPIs (loan disbursal, portfolio quality, collections, conversion funnel, customer behavior).

- Conduct deep-dive portfolio analysis on risk, vintage curves, and credit performance across products and cohorts.

- Use Excel (Advanced Functions, Pivot, Power Query, VBA, scenario analysis) and SQL for day-to-day analytics and reporting.

2. Risk & Credit Analytics (30%)

- Support the development of credit policies by analysing applicant and borrower performance.

- Build scorecards and risk models in collaboration with the credit and product teams.

- Monitor delinquency, roll rates, provisioning requirements, and recommend corrective actions.

3. Predictive Modelling & ML (20%)

- Apply advanced ML techniques (Python/R, scikit-learn, XGBoost, TensorFlow, etc.) for risk scoring, fraud detection, and early warning systems.

- Build and test predictive models to optimize lead scoring, cross-sell opportunities, and collection strategies.

4. Business Partnering (15%)

- Work with cross-functional teams (Product, Credit-Ops, Growth, Finance) to translate data insights into strategic decisions.

- Present findings clearly to senior management with actionable recommendations.

Requirements

- Bachelor's or master's degree in Statistics, Mathematics, Economics, Computer Science, or related field.

- 2-3 years of experience in data analytics roles, preferably in consumer lending fintech, banking, or credit risk.

- Advanced Excel (Pivots, Macros, VBA, What-if Analysis, Solver, Dashboards)

- Experience with BI tools (Power BI, Tableau, Looker, or similar).

- Strong SQL (complex queries, optimization, stored procedures).

- Hands-on with Python/R for data analysis and machine learning.

- Domain Knowledge: Exposure to credit risk, lending products, collections, provisioning, and regulatory reporting is highly desirable.

- Strong problem-solving skills, ability to handle large datasets, and comfort with ambiguity.