Specialist – Credit Risk & Portfolio Optimization

About the job

Job Title: Specialist – Credit Risk & Portfolio Optimization (Credit Cards) Location: Colombo, Sri Lanka Experience: 8–10 Years Project Duration: 5 months Indicative compensation range: INR 10-12 Lakhs for the project duration Role Overview This is a contractual role. As a Decision Science Lead, you will spearhead the development of advanced statistical models to manage credit risk and drive ... portfolio growth. This role requires a blend of technical mastery in predictive modelling (PD/LGD/EAD) and strategic insight to optimize credit card spends and engagement. Core Responsibilities • Model Development: Build and calibrate robust application and behaviour scorecards, including PD, LGD, and EAD models. • Forecasting & Analytics: Design loss-forecasting frameworks using Vintage, Markov, and Machine Learning (GBM/GLM) approaches. • Feature Engineering: Extract insights from bureau, transactional, device, and alternative data with rigorous quality control. • Validation & Governance: Perform back testing (KS/AUC) and stability monitoring (PSI/CSI) while ensuring model explainability via SHAP/Reason Codes. • Portfolio Optimization: Develop data models to drive credit card spends, merchant targeting, and cross-border campaign recommendations. • Regulatory Alignment: Ensure models comply with IFRS 9 / CECL accounting standards and Basel capital frameworks. Technical Skills & Qualifications • Education: Master’s in Statistics or Economics from a top-tier institution. • Tech Stack: Proficiency in Python, SQL, SAS, and Tableau. • Domain Expertise: * Deep understanding of the Credit Card Lifecycle and portfolio interventions. • Hands-on experience with Machine Learning applied to credit risk. • Expertise in IFRS 9 / CECL (Lifetime ECL, staging, and pooling). • Communication: Ability to translate complex algorithmic outputs into clear business strategies for non-technical stakeholders.

Requirements

• Predictive modelling
• Financial Analytics
• Machine Learning
• Data Engineering

Qualifications

• Master’s in Statistics or Economics

Preferred Technologies

• Predictive modelling
• Financial Analytics
• Machine Learning
• Data Engineering