Risk Analyst – Data Science & Analytics

We are looking for a Risk Analyst – Data Science & Analytics to join our Commercial Bureau Analytics & Pre-Sales Consulting team, with a dedicated focus on MSME bureau analytics. This is a hands-on role for an analyst who can use commercial credit bureau data, statistical modelling and machine learning to solve credit-risk problems for banks, NBFCs, fintechs and other MSME lenders. You will work on bureau-based risk models, scorecards, portfolio diagnostics, early-warning and segmentation use cases, while also supporting proofs of concept and analytically grounded pre-sales solutions. Strong Python and SQL skills, sound credit-risk modelling fundamentals and practical exposure to MSME / SME lending or commercial bureau data are core requirements for this role.

What you'll do

• Analyse MSME commercial bureau and lender portfolio data to support use cases across acquisition, underwriting, risk segmentation, portfolio monitoring, early warning and collections.
• Work with business-entity and facility / tradeline-level bureau information, including repayment and delinquency patterns, credit exposure and outstanding balances, utilisation, enquiries, account vintage, product mix and lender mix; combine these with permitted client, firmographic or financial attributes where relevant.
• Translate a lender use case into a structured analytical design, including outcome / bad definition, observation and performance windows, sample construction, segment definitions, data requirements and success metrics.
• Develop and validate bureau-based credit-risk scorecards and predictive models for default / serious delinquency risk, risk segmentation and related MSME credit decisions using statistically appropriate techniques.
• Engineer robust bureau variables from longitudinal and tradeline data, perform data-quality diagnostics, and create reproducible analytical datasets using Python and SQL.
• Evaluate model performance and stability using measures such as KS, Gini / AUC, lift and gains, calibration, out-of-time validation and PSI / CSI, selecting metrics appropriate to the use case.
• Perform portfolio analytics such as vintage, cohort, roll-rate, delinquency migration, concentration and risk-segment analysis to identify emerging portfolio trends and actionable insights.
• Build rapid but defensible proofs of concept for client opportunities and quantify the incremental value of bureau data, derived variables or analytical approaches over existing baselines.
• Support pre-sales consultants in client discovery, analytical solution design, methodology discussions, presentations and responses to technical questions.
• Contribute reusable bureau features, modelling utilities, templates and analytical frameworks that improve speed and consistency across recurring MSME use cases.
• Work with Product and Technology teams on UAT and productisation of repeatable analytics, and follow applicable data-security, model-governance, documentation and compliance standards.

What success looks like

• MSME bureau analyses and models are technically sound, reproducible and directly relevant to lending or portfolio decisions.
• Client proofs of concept clearly demonstrate analytical value, limitations and expected business impact within agreed timelines.
• Reusable bureau variables, code and analytical templates reduce turnaround time and improve consistency across opportunities.
• Model development and analytical outputs meet expected standards for validation, documentation, governance and quality.

What you'll need to bring

• Approximately 3+ years of experience in data science, credit-risk analytics, decision science or statistical modelling, including at least 2 years of meaningful exposure to credit-risk / lending analytics. Direct experience with MSME / SME / commercial lending or commercial bureau analytics is required.
• Strong hands-on proficiency in Python for data manipulation, feature engineering, statistical analysis and machine learning, with the ability to write structured and reusable analytical code.
• Strong SQL skills, including independent extraction, transformation and analysis of large, granular credit datasets.
• Hands-on experience developing credit-risk scorecards or predictive models using techniques such as logistic regression, decision trees, random forests / gradient boosting and segmentation / clustering, with a clear understanding of when interpretability should take precedence over model complexity.
• Practical knowledge of scorecard and model-development concepts such as binning, Weight of Evidence (WoE), Information Value (IV), variable selection, multicollinearity, train / validation / test design, class imbalance and model calibration.
• Working knowledge of MSME credit-risk concepts including delinquency and default definitions, portfolio segmentation, vintage analysis, roll rates, risk migration, early-warning indicators and portfolio monitoring.
• Experience assessing model discrimination, stability and business performance using metrics such as KS, Gini / AUC, lift / gains, PSI / CSI and out-of-time / back-testing approaches.
• Understanding of bureau data structures, aggregate facility / tradeline information to the business-entity level, identify data-quality issues and derive meaningful behavioural risk features.
• Strong analytical communication skills, including the ability to explain methodology, findings, assumptions and limitations to business and client stakeholders.

Good to have

• Hands-on experience with commercial credit bureau data, commercial credit reports, bureau scores or bureau-based MSME risk solutions.
• Experience working with MSME portfolios at banks, NBFCs, fintech lenders, business lenders or analytics / consulting firms serving these institutions.
• SAS or another statistical programming environment in addition to Python.
• Git, peer-review practices, Spark / Databricks or other tools used to work with large-scale analytical datasets.
• Exposure to model implementation, monitoring, challenger frameworks or productionisation of risk analytics.
• Awareness of model-governance, credit-information and regulatory expectations relevant to lending in India.
• Client-facing analytics, proof-of-concept, consulting or pre-sales exposure

Additional information

• Great compensation package and discretionary bonus plan
• Core benefits include pension, health Insurance and term life Insurance, Sharesave scheme and more!
• 25 days annual leave with 13 bank holidays and 3 volunteering days. You can also purchase additional annual leave.
• You will report to Senior Analytics Consultant.
• Role Location: Mumbai
• Experian is an equal opportunities employer

#LI-Onsite

Experian Careers - Creating a better tomorrow together

Find out what its like to work for Experian by clicking here