👋 Hello, I'm
Keval Savaliya
Data Scientist & ML Engineer crafting intelligent systems that transform data into actionable insights. Specialized in building production-grade ML pipelines and AI-powered solutions.
Data Scientist & ML Engineer crafting intelligent systems that transform data into actionable insights. Specialized in building production-grade ML pipelines and AI-powered solutions.
I'm a passionate Data Scientist currently pursuing my Master's in Automotive Software Engineering at Technische Universität Chemnitz, Germany. My journey in tech began with a fascination for how data can drive meaningful decisions and create intelligent systems.
With hands-on experience at Data Glacier and HackSec Infotech, I've developed expertise in machine learning, deep learning, and data analytics. I specialize in building end-to-end ML pipelines, from data preprocessing to model deployment, with a focus on creating solutions that deliver real business value.
I'm particularly excited about AI-powered applications, NLP, and computer vision, and I love exploring how emerging technologies can solve complex problems.
BERT transformer-based system that distinguishes real emergency tweets from metaphorical language. Implements state-of-the-art NLP techniques for real-time disaster detection and emergency response support.
End-to-end ML system forecasting PM10 air quality levels using XGBoost, achieving R² of 0.65 and 24% improvement over baseline. Built a production-ready REST API with automated daily data pipeline and interactive Streamlit dashboard with personalized health advisory system.
Question classifier using advanced RAG architecture with dual knowledge retrieval systems, improving response accuracy by 40%. Implemented intelligent routing with LLM-based classification.
An intelligent email monitoring system using LLM-based content analysis to automatically detect interview invitations, achieving 90%+ accuracy with automated data pipeline integration.
Interactive AI application leveraging Claude Sonnet 4.5 for personalized workout recommendations and real-time guidance with dynamic workout adjustments.
Comprehensive analytics dashboard monitoring KPIs and consumer behavior, identifying 20%+ Revenue optimization opportunities with extensive SQL data quality audits.
Time-series forecasting system using Stacked LSTM neural networks, achieving 85% prediction accuracy with real-time data acquisition from the yfinance API.