Data Scientist– Credit Risk Modelling

Domain: Retail Banking / Credit Cards

Location: Mumbai

Experience: 3–5 years

Industry: Banking / Financial Services

Why would you like to join us?

TransOrg Analytics specializes in Data Science, Data Engineering and Generative AI, providing advanced

analytics solutions to industry leaders and Fortune 500 companies across India, the US, APAC and the

Middle East. We leverage data science to streamline, optimize, and accelerate our clients' businesses.

Visit www.transorg.com to learn more about us.

What do we expect from you?

 Build and validate credit risk models, including application scorecards and behavior

scorecards (B-score), aligned with business and regulatory requirements.

 Use advanced machine learning algorithms such as Logistic Regression, XGBoost, and

Clustering to develop interpretable and high-performance models.

 Translate business problems into data-driven solutions using robust statistical and analytical

methods.

 Collaborate with cross-functional teams, including credit policy, risk strategy, and data

engineering, to ensure effective model implementation and monitoring.

 Maintain clear, audit-ready documentation for all models and comply with internal model

governance standards.

 Track and monitor model performance, proactively suggesting recalibrations or

enhancements as needed.

What do you need to excel at?

 Writing efficient and scalable code in Python, SQL, and PySpark for data processing, feature

engineering, and model training.

 Working with large-scale structured and unstructured data in a fast-paced banking or fintech

environment.

 Deploying and managing models using MLFlow, with a strong understanding of version

control and model lifecycle management.

 Understanding retail banking products, especially credit card portfolios, customer behavior,

and risk segmentation.

 Communicating complex technical outcomes clearly to non-technical stakeholders and senior

management.

 Applying a structured problem-solving approach and delivering insights that drive business

value.

What are we looking for?

 Bachelor’s or master’s degree in Statistics, Mathematics, Computer Science, or a related

quantitative field.

 3–5 years of experience in credit risk modelling, preferably in retail banking or credit cards.

 Hands-on expertise in Python, SQL, PySpark, and experience with MLFlow or equivalent

MLOps tools.

 Deep understanding of machine learning techniques, including Logistic Regression, XGBoost,

and Clustering.

 Proven experience in developing Application Scorecards and behavior Scorecards using real-

World Banking Data.

 Strong documentation and compliance orientation, with an ability to work within regulatory

frameworks.

 Curiosity, accountability, and a passion for solving real-world problems using data.

 Cloud Knowledge, JIRA, GitHub(good to have)