I'm a first-year engineering student at IGDTUW, passionate about building intelligent systems at the intersection of NLP, financial data, and accessible technology. I like turning messy, real-world data into something that actually makes decisions better.

• 🧠 Working with FinBERT, sentiment pipelines, and volatility-aware feature engineering
• 🌱 Currently deepening my knowledge of ML systems and cloud architecture
• 🏆 National finalist — Top 10 of 581 teams at HackwithMAIT 6.0 (Top 1.7%)
• 📬 Reach me at harshprabha95@gmail.com

An end-to-end NLP pipeline for financial news sentiment classification using FinBERT.

• Designed a Sentiment Reliability Index (SRI) with a validation score of 67.9 for confidence-weighted signal reliability
• Engineered a feature pipeline integrating news sentiment, VIX volatility data, and price trends
• Automated real-time data ingestion via REST APIs; preprocessing with Pandas & NumPy; inference in PyTorch

A responsive, accessible community learning web app — built in 24 hours at HackwithMAIT 6.0.

• Top 10 nationally out of 581 teams
• Built with HTML5, CSS3, JavaScript + Firebase (Auth & Firestore real-time database)

Languages      Python · Java · JavaScript
ML / NLP       PyTorch · FinBERT · Pandas · NumPy · Sentiment Analysis · Feature Engineering
Web            HTML5 · CSS3
Database       Firebase (Firestore · Authentication)
Tools          Git · GitHub · VS Code · Google Cloud Platform

• 📡 Tech & Event Coordinator @ IEEE IGDTUW — managing technical workshops and open-source events
• 📝 Research Coordinator @ E-Cell IGDTUW — authoring weekly tech & startup ecosystem newsletters