Lead - Model Developer

Model Development:

1. Design and Build Models:

• Develop predictive and prescriptive models using machine learning, statistical, and AI techniques.
• Focus on areas such as credit risk scoring, fraud detection, customer churn, marketing analytics, and portfolio optimization.

1. Data Preparation and Analysis:

• Collect, clean, and preprocess large datasets from multiple sources.
• Perform exploratory data analysis (EDA) to identify trends, patterns, and insights.

1. Algorithm Selection and Implementation:

• Select appropriate algorithms (e.g., regression, decision trees, neural networks, etc.) based on business requirements.
• Implement models using programming languages like Python, R, or SAS.

1. Model Deployment:

• Collaborate with IT and business teams to deploy models into production systems.
• Ensure models are scalable, efficient, and integrated with existing banking systems.

1. Performance Monitoring:

• Monitor model performance post-deployment and make necessary adjustments.
• Develop dashboards and reports to track key metrics and outcomes.

Model Validation:

1. Independent Validation:

• Conduct independent validation of models developed by other teams to ensure accuracy, robustness, and compliance with regulatory standards.
• Assess model assumptions, methodologies, and data inputs.

2. Testing and Benchmarking:

• Perform back-testing, stress-testing, and sensitivity analysis to evaluate model performance.
• Compare model outputs with alternative approaches or benchmarks.

3. Documentation and Reporting:

• Prepare detailed validation reports, including findings, recommendations, and risk assessments.
• Ensure all models comply with internal policies and regulatory requirements (e.g., SR 11-7, Basel III).

4. Stakeholder Collaboration:

• Work closely with model developers, risk managers, and auditors to address validation findings.
• Provide guidance on model improvements and risk mitigation strategies.

Qualifications

Education:

• Bachelor's/ Masters degree in Finance, Business Administration, Risk Management, Accounting, or related field.

Experience:

• Preferably 4-8 years of experience in data science, model development, and validation, preferably in the banking or financial services industry.
• Hands-on experience with machine learning, statistical modelling, and AI techniques.
• Proven experience in managing a risk and control self-assessment program at the organizational level.
• Familiarity with regulatory frameworks and risk management standards is a plus.

Technical Skills:

• Proficiency in Microsoft Excel, PowerPoint, and risk management concepts & techniques.
• Experience with risk management software, dashboards, or reporting tools is a plus.
• Proficiency in programming languages such as Python, R, or SAS.
• Strong knowledge of machine learning frameworks (e.g., TensorFlow, Scikit-learn, PyTorch).
• Experience with big data tools (e.g., Hadoop, Spark) and cloud platforms (e.g., AWS, Azure) is a plus.
• Familiarity with banking data systems and regulatory requirements.

Key Competencies

• Proven ability to lead and drive change, taking full ownership of the RCSA process and ensuring its effectiveness.
• Deep knowledge of operational risk management, aligning risk management practices with organizational goals.
• Skilled in engaging stakeholders at all levels and effectively communicating risk assessments and recommendations.
• Able to identify risks, evaluate controls, and make decisions to improve processes and mitigate risks.
• Experienced in collaborating across teams and maintaining strong relationships with key business units.
• Capable of adapting the RCSA process to address emerging risks and regulatory changes.
• Experience with credit risk models, fraud detection models, or customer lifetime value (CLV) models