Data Scientist / Data Analyst – IDFC FIRST Bank

Opportunity Overview

Banking Analytics & Model Governance Life Cycle

The Data Scientist / Data Analyst at IDFC FIRST Bank works at the intersection of quantitative techniques and banking business strategy, translating source-system data into actionable predictive models and decision frameworks:

┌───────────────────────────────────────────┐
│ 1. Business Requirements & Portfolio Scoping │ ➔ Partner with business stakeholders to define analytical goals for banking portfolios
└─────────────────────┬─────────────────────┘
                      ▼
┌───────────────────────────────────────────┐
│ 2. Data Exploration & Variable Engineering│ ➔ Explore raw source systems & data marts using PySpark/SAS to build predictive features
└─────────────────────┬─────────────────────┘
                      ▼
┌───────────────────────────────────────────┐
│ 3. Model Development & Validation        │ ➔ Train robust ML models & statistical algorithms; audit against governance metrics
└─────────────────────┬─────────────────────┘
                      ▼
┌───────────────────────────────────────────┐
│ 4. Deployment, Mentorship & Control        │ ➔ Deploy automated frameworks, mentor junior analysts, & track business outcomes
└───────────────────────────────────────────┘

Key Responsibilities

• Techno-Functional Modeling: Scope business priorities across banking portfolios (credit risk, retail assets, customer acquisition, or cross-sell) and translate them into machine learning frameworks.

• Big Data Exploration & Feature Engineering: Perform deep-dive exploration across banking data marts using PySpark, Python, and SAS to derive variable ideas and feature sets.

• Model Governance & Monitoring: Develop predictive models while managing validation standards, variable drift, tracking metrics, and regulatory governance compliance.

• Team Leadership & Coaching: Direct and mentor a team of junior Data Analysts, reviewing cases and maintaining output quality.

• Stakeholder Alignment: Build strong partnerships across product, risk, and business operations to drive model adoption and business impact.

Qualification Matrix & Technical Skill Stack

Core Requirements

Key Focus Areas for Interview Preparation

1. Banking Portfolio & Credit Risk Analytics: Review core banking analytical use cases, including Application/Behavioral Credit Scoring, Churn Prediction, LTV Modeling, NPA Forecasting, and Propensity Models.

2. PySpark & Distributed Data Processing: Practice PySpark operations on large datasets (e.g., handling missing values, window functions, feature transformations, performance optimization, and memory management).

3. Model Governance & Tracking Metrics: Prepare to explain key model performance and stability metrics, such as Gini/AUC, PSI (Population Stability Index), CSI (Characteristic Stability Index), and KS Statistic.