Baoying Huang

• Data Analytics: Leveraged SQL and Python to develop and implement fraud detection algorithms, achieving a 50% reduction in false positives while optimizing operational costs and enhancing customer experience for cheque and payment portfolios.
• Business Intelligence & Visualization: Developed a suite of interactive Power BI dashboards to monitor key business metrics, facilitating data-driven decision-making for the management team.
• Efficiency Improvement: Designed and implemented a data model using SQL and Python to streamline reporting processes, resulting in a 30% reduction in report generation time.
• Cohort Analysis: Conducted detailed cohort analysis to identify and interpret behavioral trends, providing actionable insights for strategic decision-making.
• Data Segmentation & Modeling: Analyzed and synthesized complex business requirements from diverse datasets, enabling targeted strategy development and enhancing fraud detection effectiveness.
• Data Enrichment: Conducted an in-depth analysis of Enterprise Data Warehouses (EDW) to pinpoint features associated with fraudulent behaviors. Collaborated closely with cross-functional teams to integrate these features into a centralized fraud feature store, significantly enhancing model accuracy and operational efficiency.
• Performance Monitoring and Reporting: Developed KPI dashboards using Power BI to continuously monitor the performance of fraud detection strategies. Adjusted fraud alert priorities based on dashboard insights and communicated changes to stakeholders to ensure alignment and operational buy-in.

Leveraged SQL and Python to develop and implement fraud detection algorithms, achieving a 50% reduction in false positives while optimizing operational costs and enhancing customer experience.
Designed and implemented a data model using SQL and Python to streamline reporting processes, resulting in a 30% reduction in report generation time.
Conducted detailed cohort analysis to identify and interpret behavioral trends, providing actionable insights for strategic decision-making.
Analyzed and synthesized complex business requirements from diverse datasets, enabling targeted strategy development and enhancing fraud detection effectiveness.
Performed a comprehensive analysis of Enterprise Data Warehouses (EDW) to identify key features indicative of fraudulent activities.
Collaborated extensively with cross-functional teams to integrate these features into a centralized fraud feature store.
Leveraged these enriched features to develop and refine fraud detection models and rules, resulting in significant improvements in model accuracy and operational efficiency.
Developed KPI dashboards using PowerBI to continuously monitor the performance of fraud detection strategies.
Conducted detailed analysis to determine the necessity of strategy modifications or retirements.
Adjusted fraud alert priorities for the operations team based on dashboard insights.
Effectively communicated these changes to stakeholders to ensure alignment and operational buy-in.

Deployed comprehensive data input process through vendor and in-house systems in adherence to service-level agreement requirements.
Achieved efficient execution with productivity.
Performed data entry and validation for RESP operation.
Investigated data deficiencies and generated operation reports.
Improved fund operation workflow.