Khalid V

Data Analyst @Bank of America

US

Addressed inconsistent regulatory data mappings by designing robust attribute lineage from source systems to Finance & Regulatory Reporting data marts, resulting in improved data traceability and audit readiness.• Automated end-to-end data ingestion and transformation by integrating Google Cloud Storage with Big Query, enabling real-time access to raw loan records and reducing manual data prep time by 40% for reporting and analysis.• Designed and executed SQL transformations in Big Query to clean and standardize unstructured loan application data, which empowered the analytics team to build accurate approval trend dashboards and improve risk segmentation strategies by 25%.• Accelerated project timelines by building reusable, unit-tested code to automate mapping logic for recurring datasets, reducing manual intervention by 40%.• Built and automated an SAS-based data pipeline to clean, transform, and model over bank loan applications, improving data accuracy by 30% and enabling stakeholders to confidently evaluate applicant risk and loan eligibility.• Designed and implemented a linear regression model using PROC REG in SAS to predict loan amounts based on income and employment history, which helped the credit team improve loan decision turnaround time by 25% and align offers with risk profiles.• Improved SQL performance and target data structure alignment by contributing to ERD and data model enhancements, optimizing query execution time by 20%.• Leveraged tools such as GCP (Big Query), Ab Initio, Python, SAS, and SQL to transform and deliver accurate, timely data assets supporting critical finance and risk reporting initiatives.