Vinay Hulsurkar.

Python | Pandas | Scikit-learn | Streamlit | Plotly

• System Architecture: Architected a robust financial analytics web application capable of parsing raw transactional data to identify spending anomalies.
• Machine Learning Integration: Implemented Isolation Forest for anomaly detection and time-series forecasting models to estimate future expenditure.
• Data Visualization: Designed highly interactive analytical dashboards to compute and display a dynamic Financial Health Score.

Python | Pandas | Matplotlib | Seaborn | Time-Series

• Quantitative Analysis: Processed and analyzed 5+ years of historical market data (~50,000 data points) to model price volatility and support/resistance zones.
• Forecasting: Developed moving-average statistical models to detect short-term momentum shifts and potential algorithmic trading signals.

Python | Scikit-learn | Streamlit | Plotly

• Machine Learning & Analytics: Built a property valuation tool for 10 Indian cities using synthetic data (~5K records), training a Random Forest model (R² ≈ 0.97) for price prediction and CAGR-based forecasting.
• Financial Logic & Visualization: Integrated credit risk parameters (DTI & LTI) to evaluate loan eligibility and EMI affordability, presenting insights through an interactive UI supported by dynamic visualizations.

Python | RAG Architecture | Vector DB | Ollama | Streamlit

• AI Integration: Engineered a local Retrieval-Augmented Generation (RAG) system enabling semantic search and Q&A over custom user documents.
• Vector Search: Implemented vector embedding similarity retrieval to feed high-context data into locally running Large Language Models (LLMs).