Detect and classify fraudulent transactions using SQL and Python. Generate behavioral features with SQLite, train a Logistic Regression model, and evaluate performance with AUC, precision, recall, and ROC analysis. A complete supervised fraud detection workflow.

Mutual Fund Analysis Dashboard using Python, Excel, and Power BI | Top 30 Low-Risk High-Return Schemes Identified

Detect suspicious financial transactions using SQL and Python. Build user-level behavioral features in SQLite, apply Isolation Forest for anomaly detection, and visualize high-risk patterns. Demonstrates unsupervised fraud analytics and SQL-driven data science workflow.

Personal investing tracker with watchlist, portfolio analytics, and corporate events tracking. Built with Next.js 15, tRPC v11, Prisma, and InfluxDB.

This repository contains results of the completed tasks for the Quantium Data Analytics Virtual Experience Program by Forage, designed to replicate life in the Retail Analytics and Strategy team at Quantium, using Python.

Demonstrates a workflow that involves fetching, processing, storing, analyzing, and reporting on financial data using machine learning techniques within a Snowflake database environment

This repository contains all lab work and digital assessments from the Winter Semester of my M.Sc. Data Science program at VIT Vellore. Projects span across machine learning, data mining, statistical inference, time series analysis, data visualization, and Java programming—implemented using tools like Python, R, Power BI, Tableau, Excel, and Java

Production-style financial data engineering pipeline that standardizes NSE equity fundamentals into a query-optimized SQLite warehouse.

End-to-end Credit Risk engine using Python. Achieved 93.04% Cross-Validated Recall and 0.98 ROC-AUC. Implemented advanced preprocessing (Log/Robust Scaling) and SMOTEENN to handle class imbalance. Champion model (Logistic Regression) provides full interpretability for strategic financial risk mitigation. 🏦📈

Interactive Power BI dashboard analyzing credit card transactions to uncover spending patterns, customer insights, and key financial KPIs for data-driven decision-making.

End-to-end KYC/AML compliance data analysis using mock datasets. Includes customer risk scoring, suspicious transaction flagging, and compliance reporting in Python (Pandas, Matplotlib).

Chrome extension for comprehensive expense tracking and financial analysis, empowering users with automated e-commerce price detection, OCR receipt scanning, and real-time budget monitoring across multiple currencies.

Portfolio Risk Simulator is an interactive web app that lets users build portfolios, analyze risk with VaR and Sharpe ratios, visualize correlations, and compare performance to benchmarks, uses real-time data.

In this project, I analyze commercial sales data using NumPy and pandas. I visualize total revenue per product using color-coded bar charts in Matplotlib. It’s a foundational step in business data analysis and project documentation.

🚀 AlphaCrew: Production-grade multi-agent hedge fund platform powered by CrewAI Enterprise. Features live trading via Alpaca, real-time performance monitoring with Grafana, and human oversight through Slack. Built for sophisticated algorithmic trading and portfolio management.

🏦🤖FinChurn is an advanced Financial Machine Learning system designed to predict customer churn and detect fraudulent activities with high accuracy. It includes a complete end-to-end ML workflow covering data preprocessing, exploratory analysis, class imbalance handling (SMOTE)

Automated financial reconciliation and business analytics platform for theater operations. Reduced reconciliation time by 90%.

modeling of pricing and analysis of stock and options

An analytical study of how Bitcoin market sentiment (Fear vs Greed Index) influences trading volume, leverage behavior, and profitability using historical data.

End-to-end analysis of bank loan default risk using historical lending data to identify key risk factors, assess borrower behavior, and support data-driven credit decisions.

Financial Analytics + ML: Databricks Data Lakehouse, Delta Lake, 4 ML models (RF, Isolation Forest, K-Means, Prophet), MLflow, Streamlit dashboard

Machine learning project predicting loan defaults using HMEQ dataset. Implements multiple classification algorithms (Logistic Regression, Decision Tree, Random Forest) with comprehensive EDA and model evaluation. Capstone project for MIT ADSP Program

End-to-end Python notebook that engineers a proxy “bad-client” label, explores drivers of credit risk, and builds a leakage-free XGBoost scorecard with threshold tuning and cross-validation.

📊 End-to-end data analytics project analyzing a bank’s loan portfolio to identify profitable segments, high-risk borrowers, and strategic insights using Python, Jupyter Notebook, and data visualization.

Full-stack personal finance dashboard with transaction tracking, data visualization, and AI-powered forecasting. Built with FastAPI, React, Chart.js, and SQLAlchemy. Features JWT auth, CSV import/export, and glassmorphism UI.

Analyzing $33B in lending data across 2 Million+ records to identify credit risk patterns using Python, SQL, and Power BI.

A Multi-Agent AI System that connects Tally Prime with Google Gemini for real-time financial analytics, automated reporting, and dynamic visualization.

This project involves a comprehensive data analysis of stock market trends and performance. The analysis aims to uncover patterns, trends, and insights that can aid in making informed investment decisions. By leveraging various data analytics techniques, this project provides valuable visualizations and interpretations of stock market data.

This project documents the development of a Python-based Forex trading algorithm that integrates technical indicators and news analytics to automate trading strategies on MetaTrader 5.

Advanced SQL analytics demonstrating window functions, CTEs, and cumulative calculations — techniques directly applicable to financial services reporting.