Raviteja Gattupalli

Assistant Manager @Bank of America

Hyderabad, IN

Implemented scalable data pipelines to process terabytes of bank customer data for fraud detection using Spark andHive,performing necessary transformations, schema validation, and data quality checks2. Performed data analysis to identify anomalies, designed a data model for efficient storage, and developed a graphdatabase schema for seamless data ingestion and relationship mapping3. Ingested and processed data into TigerGraph (Graph Database) to compute high-level feature values critical for fraud detection. These features included one-hop and two-hop relationships between key customer identifiers, as well as various connections and associations linking different customer attributes, enabling more accurate and insightful fraud analysis4. Implemented a pipeline to process and publish computed features, along with delta updates of feature values, to Kafkaand Hive tables, enabling data scientists to build and refine advanced fraud detection models5. Converted legacy Hive queries to PySpark, optimizing data processing efficiency. Automated manual report generationusing PySpark, reducing processing time and increasing overall productivity

FIITJEE

12th Class

R.V.R. & J.C. College of Engineering

Bachelor of Technology - BTech, Information Technology