Pandraju Gamanapriya

About

Healthcare data/NLP practitioner with experience at UnitedHealthcare building production ML systems that connect unstructured call center transcripts and medical notes to structured claims data. Has delivered measurable impact (25% classification accuracy lift; ~30% relevance improvement) using classical NLP, embeddings (Sentence-BERT + FAISS), and AWS SageMaker deployments with robust validation and drift monitoring.

Key Strengths

• Built NLP pipeline linking unstructured call transcripts to structured claims data
• Improved case classification accuracy ~25% and reduced manual triage time
• Strong model validation practice (cross-validation, stratified sampling, ROC-AUC/F1, confusion matrix, GridSearch)
• Production deployment on AWS SageMaker with monitoring/drift checks against actual outcomes
• Entity resolution/data cleaning with fuzzy matching and manual audit (5% sample) achieving ~96% precision
• Embedding-based linking/search using Sentence-BERT + FAISS improving match relevance ~30%
• Domain fine-tuning with triplet loss to improve healthcare contextual accuracy
• Production-grade data workflows with Airflow/Spark, testing, logging, and CI/CD

Experience

Education

Skills

Languages