Chandana Gaddam

Performed data analysis on a large-scale dataset of 100K+ Bills of Lading documents using Python and SQL, extracting and standardizing key shipping details. Applied data management, monitoring, and profiling practices, improving accuracy and consistency by 20% while reducing anomalies and missing values by 15% across logistics records. Built Power BI dashboards to visualize shipment trends, cutting reporting time by 30%. Leveraged Gemini 1.5 Pro LLM for natural language–to–SQL query generation, streamlining large document-to-database integration and improving query efficiency by 25%.

Developed retrieval-based query pipelines on large-scale medical insurance billing data using SQL and NLP techniques, automating structured data extraction and reducing query latency by 50%. Managed large-scale data preprocessing and validation (cleaning, normalization, feature engineering), improving accuracy and reliability of insurance claim prediction models. Conducted in-depth analysis of billing data, uncovering trends and anomalies to support fraud detection and claims optimization. Implemented data monitoring and profiling workflows, reducing preprocessing errors by 20% and ensuring high-quality input for ML models.