Credit Risk Modelling

Role & responsibilities

• Extract, clean, and preprocess financial datasets for model development.
  
• Perform exploratory data analysis (EDA) to identify trends and variable relationships.
  
• Define bad definition, observation, and performance windows.
  
• Develop PD, LGD, and EAD models as per Basel III / IFRS9 guidelines.
  
• Build Application, Behavioral, and Collection scorecards for retail/wholesale portfolios.
  
• Apply statistical and machine learning techniques (Logistic Regression, Decision Trees, Random Forest, etc.).
  
• Conduct variable selection, transformation, and feature engineering.
  
• Evaluate model performance using KS, Gini, AUC, calibration, and stability tests.
  
• Perform out-of-sample and out-of-time validations.
  
• Document model methodology, assumptions, and development process.
  
• Ensure compliance with Basel, IFRS9, CCAR, and internal MRM frameworks.
  
• Support regulatory reviews, internal audit, and model validation queries.
  
• Implement model monitoring and recalibration processes.
  
• Track portfolio drift, PSI, and model performance metrics.
  
• Conduct root cause analysis for threshold breaches or degradation.
  
• Automate model monitoring and reporting dashboards using Python, SAS, or SQL.
  
• Prepare technical documentation and presentations for senior management.
  
• Collaborate with business, risk, data, and IT teams for model deployment.
  
• Maintain model inventory, change logs, and governance documentation.
  
• Stay updated on regulatory and quantitative modeling best practices.
  

Preferred candidate profile

• 10 years of experience in credit risk modeling, scorecard development, or risk analytics within banking or BFSI.
  
• Strong understanding of Basel II/III, IFRS9, CCAR, and CECL regulatory frameworks.
  
• Proven experience in developing PD, LGD, and EAD models for retail and wholesale portfolios.
  
• Hands-on proficiency in SAS, Python, SQL, and advanced statistical modeling techniques.
  
• Solid knowledge of statistical and machine learning methods (Logistic Regression, Decision Trees, Random Forests, etc.).
  
• Experience in model documentation, validation support, and model performance monitoring.
  
• Familiarity with model governance, MRM standards (SR 11-7, ECB TRIM), and audit processes.
  
• Exposure to IFRS9 impairment modeling and portfolio analytics (vintage, roll-rate, delinquency analysis).
  
• Strong quantitative and analytical skills with background in Statistics, Mathematics, Economics, or Quantitative Finance.
  
• Excellent communication and presentation abilities for stakeholder engagement.
  
• Certifications such as FRM, PRM, or CFA preferred.
  
• Experience working with global banking clients or in a regulatory-driven environment is highly