Data Analyst (Credit Risk Modelling)

Responsibilities:

• Data Handling and Preprocessing: Perform data cleansing, merging, and enrichment, ensuring high-quality datasets for scorecard development. Handle large-scale financial datasets and transform them into actionable insights for credit risk scoring.
• Feature Engineering: Extract and engineer meaningful features from raw financial data to enhance the predictive power of credit risk models. Perform advanced feature selection techniques to optimize model performance.
• Risk Model Development: Build, test, and refine machine learning algorithms to predict credit risk, leveraging a mix of traditional and advanced analytical approaches.
• Regulatory Compliance and Transparency: Ensure that all credit risk models comply with industry regulations and internal standards. Use best practices for model governance, ensuring transparency and traceability throughout the process.
• Business Insights and Reporting: Conduct exploratory and targeted data analyses to gain actionable insights and support the development of new strategies for assessing and managing credit risk.
• Model Performance Tracking: Continuously track the performance of deployed credit risk models, analyze any deviations, and ensure models meet business expectations and regulatory standards.

Key Success Metrics:

• Model Accuracy and Risk Mitigation: Ensure the development and implementation of accurate credit risk models that effectively mitigate business and financial risk. Business.
• Outcomes and Impact: Contribute to reducing default rates, enhancing credit approval accuracy, and driving profitability through advanced predictive analytics.
• Revenue Growth and Profitability: Drive revenue growth by ensuring that credit risk models enable profitable lending decisions and support sound credit policies.
• Model and Tool Development: Successfully develop and deploy credit risk models that align with business strategies and meet quality standards.
• Model Optimization and Enhancement: Continuously enhance model performance and efficiency through regular monitoring, backtesting, and recalibration of models.
• Strategic Campaign Design: Independently design strategies for credit risk campaigns, including credit limit adjustments, delinquency management, and credit portfolio optimization.
• Tracking and Monitoring: Regularly track and report on the performance of credit risk models to ensure they meet business and risk management goals.

Requirements:

• Proven experience in developing and deploying credit risk models (e. g., application scoring, behavioral scoring).
• Solid understanding of credit risk assessment techniques, including statistical, machine learning, and traditional risk modeling approaches.
• Experience in using data science and statistical software (e. g., Python, PySpark) for data analysis and model development.
• Strong communication skills, with the ability to present complex analytical results to non-technical stakeholders.
• Experience in model deployment practices.
• Graduate (Full-time): Master's/Bachelor's in Mathematics, Computer Science, Engineering, Statistics, Economics, Finance, or a related field.