Data Scientist - Credit Risk/Predictive Modeling
First seen by Alion on Sep 11, 2026.
We are looking for an experienced Data Scientist with strong expertise in credit risk, credit bureau analytics, and predictive modeling within the BFSI domain. The ideal candidate should have hands-on experience developing and productionizing statistical and machine learning models, translating credit and business problems into analytical solutions, and partnering with business, risk, policy, fraud, and product teams.
Responsibilities :
- Translate complex credit risk and business problems into end-to-end data science problems and scalable analytical solutions.
- Design, develop, validate, and deploy statistical and machine learning models for credit underwriting, risk segmentation, portfolio analytics, and related use cases.
- Leverage credit bureau data to generate insights and improve underwriting strategies, customer segmentation, risk assessment, and portfolio performance.
- Develop and optimize predictive models using techniques such as Logistic Regression, Linear Regression, Gradient Boosting, and other machine learning/deep learning approaches.
- Perform data exploration, feature engineering, model development, validation, performance monitoring, and model enhancement.
- Work with large and complex datasets using Python, R, Spark, and/or Databricks.
- Productionize machine learning models and collaborate with technology/MLOps teams on deployment, monitoring, retraining, and lifecycle management.
- Partner with Credit Policy, Credit Risk, Fraud Risk, Collections, Operations, Product, and Business teams to ensure models address key business objectives.
- Analyze model performance and portfolio trends and provide actionable recommendations to improve credit outcomes and business performance.
- Present model results, analytical findings, performance metrics, and strategic recommendations to senior management and business stakeholders.
- Identify new opportunities to apply advanced analytics and machine learning across the credit lifecycle.
- Mentor junior data scientists and analysts, provide technical guidance, and contribute to improving data science practices and capabilities.
- Ensure appropriate documentation, validation, governance, and monitoring of analytical models and solutions.
Requirements:
- 4 - 9 years of hands-on experience in Data Science, Data Analytics, or Machine Learning, with significant experience in credit risk and/or credit bureau analytics within BFSI.
- Strong hands-on experience in credit risk modeling, bureau analytics, underwriting, risk segmentation, or portfolio analytics.
- Strong mathematical and statistical foundation with practical experience in predictive modeling.
- Hands-on experience with Logistic Regression, Gradient Boosting/GBM, Linear Regression, and other machine learning techniques; exposure to deep learning is preferred.
- Advanced proficiency in Python and strong working knowledge of R, Spark, and/or Databricks.
- Experience working with large-scale customer, transactional, financial, and credit bureau datasets.
- Hands-on experience with model deployment, productionization, monitoring, and model lifecycle management.
- Strong understanding of model performance evaluation, feature engineering, validation, and statistical analysis.
- Experience collaborating with cross-functional teams across Credit, Risk, Fraud, Collections, Policy, Operations, and Product.
- Strong analytical reasoning, data interpretation, problem-solving, and structured thinking skills.
- Excellent communication and stakeholder management skills, with the ability to present complex analytical concepts to non-technical stakeholders.
- Experience mentoring team members or providing technical guidance is preferred.
- Bachelor's or Master's degree in Statistics, Mathematics, Computer Science, Data Science, Economics, Engineering, or another quantitative discipline.
Skills
Data Science, Data Scientist, Credit Risk Modeling, Data Risk Management, Analytics, Statistical Modeling, Machine Learning, Data Analytics, Python, Predictive Modeling, Data Strategy