Shambhavi Adhikari

Fine-tuning BioBERT per disease for clinical NER on 40,000 notes. Knowledge graph linking diseases, symptoms, and treatments for RAG-based retrieval.

Processed Fannie Mae data in Parquet with Spark. Clustering, regression, and risk analysis on corporate filings using PySpark and Neo4j GraphRAG.

Content-based image retrieval for 12K artworks using SimCLR. FAISS nearest-neighbor search achieving 96% top-10 similarity accuracy.

CNN, CRNN, and Vision Transformer models classifying animal sounds from Mel-spectrograms. Tuned CNN+Dropout outperformed YAMNet — 92% test accuracy.

Quantified receiver separation, reaction time, and coverage efficiency from frame-level tracking data. K-Means clustering for defensive movement archetypes.

Leveraged YouTube API telemetry to identify a monetization sweet spot and uncover a growth opportunity through CTR optimization across channels.