Key Accountabilities
Machine Learning Model Development
• Design and develop machine learning models for pricing optimization, including dynamic pricing, rate optimization, and fee structures
• Build propensity models for customer behavior prediction, including churn, cross-sell, upsell, and product adoption
• Develop recommendation systems for personalized product offerings, next-best-action, and customer engagement
Banking Domain Application
• Apply deep banking domain knowledge to frame business problems as machine learning solutions with measurable outcomes
• Partner with Risk, Finance, and business units to identify high-value modelling opportunities
• Ensure models incorporate relevant regulatory requirements, risk considerations, and business constraints
Analysis & Insights
• Conduct exploratory data analysis to identify patterns, relationships, and modelling opportunities in banking data
• Translate model outputs into actionable business recommendations and insights
• Develop model performance metrics aligned with business KPIs and financial outcomes
• Create data visualizations and reports for stakeholder communication
Prototyping & Delivery
• Develop working prototypes in Python demonstrating model functionality and business value
• Create clear documentation of model methodology, assumptions, limitations, and use cases
• Collaborate with ML Engineers and AI Engineers to transition prototypes into production systems
Stakeholder Collaboration & Governance
• Partner with business stakeholders to understand requirements and validate model outputs
• Present model results, methodology, and recommendations to senior management
• Contribute to model governance, validation, and documentation requirements
• Ensure compliance with data policies, ethical standards, and regulatory requirements
Key Competencies
Machine Learning & Statistics
• Expert knowledge of supervised and unsupervised learning techniques for classification, regression, and clustering
• Deep experience with pricing models, propensity modelling, and recommendation systems
• Strong foundation in statistical analysis, hypothesis testing, and experimental design
• Familiarity with deep learning frameworks such as TensorFlow and PyTorch
Banking Domain Expertise
• Comprehensive understanding of banking products (Retail or Corporate), services, and customer lifecycle
• Knowledge of Risk functions, including credit risk, market risk, and operational risk frameworks
• Understanding of Finance functions, including P&L drivers, cost allocation, and profitability analysis
• Familiarity with regulatory requirements impacting model development (e.g., IFRS 9, Basel)
Technical Skills
• Python for data analysis and model development (pandas, scikit-learn, XGBoost, etc.)
• Advanced SQL skills, including stored procedures, window functions, temporary tables, and recursive queries
• Experience with data visualization and reporting tools
• Familiarity with Git (GitHub/GitLab) for version control
• Basic understanding of Spark for large-scale data processing
• Awareness of MLOps practices and model deployment concepts (MLflow, TFX)
Communication & Collaboration
• Ability to translate complex analytical concepts into business language for non-technical stakeholders
• Strong executive-level presentation skills
• Experience working with cross-functional business and technology teams
• Experience with Agile methodologies (Kanban, Scrum)
Qualifications & Experience
• Master's degree or PhD in Finance, Economics, Statistics, Mathematics, or a quantitative field (strongly preferred)
• 8+ years of experience in data science or quantitative analysis roles
• Minimum 5 years of experience in the banking or financial services industry (mandatory)
• Proven track record of delivering ML models in pricing, propensity, or recommendation domains
• Background in Risk, Finance, or quantitative banking functions preferred
• Experience with model validation, governance, and regulatory requirements in financial services
• Professional certifications in Risk (FRM, PRM) or Finance (CFA) are a plus
