Job Purpose
Lead the development and institutionalization of Machine Learning (ML) capabilities within the credit modelling function, complementing traditional scorecard methodologies. This role is responsible for driving innovation in credit risk modelling, establishing robust ML governance and MLOps practices, and enhancing model performance through the use of advanced analytics, alternative data, and scalable model frameworks.
Key Responsibilities
- Drive the design, development and deployment of ML-based credit models, including application, behavioural and alternative scoring models across SME, Digital SME and retail portfolios.
- Establish and embed end-to-end MLOps capabilities, including model lifecycle management, performance monitoring, automated refresh frameworks and integration with enterprise systems and data infrastructure.
- Lead research and adoption of advanced analytics techniques and alternative data sources (e.g. transactional, behavioural, device-based data) to enhance model coverage and predictive power, particularly for thin-file segments.
- Oversee model performance monitoring and support validation processes to ensure robustness, interpretability and compliance with internal model risk management frameworks and regulatory standards.
- Collaborate closely with Credit, Business, Finance, IT and Model Validation teams to ensure successful implementation, stakeholder alignment and effective communication of model outcomes.
- Build and lead a high-performing team of data scientists and risk modellers, fostering strong technical capability in ML and promoting a culture of innovation and continuous improvement.
Qualifications
- Bachelors or Masters Degree in data science, statistics, mathematics, actuarial science, computer science or related quantitative field.
- Minimum 8 – 12 years of experience in credit risk modelling, with proven experience in developing and implementing ML-based models in a banking or financial institution.
- Strong understanding of predictive modelling techniques, including both traditional scorecards and modern ML approaches (e.g. gradient boosting, random forest, neural networks).
- Proficiency in programming languages such as Python, SAS and SQL, with familiarity in ML frameworks and data platforms.
- Deep understanding of model risk management, validation requirements and regulatory expectations in banking.
- Strong leadership, stakeholder management and communication skills, with the ability to translate complex technical concepts into actionable business insights.
- Possesses strong quantitative and analytical thinking, with the ability to balance innovation with practical implementation and governance.
