Student Expense Tracker with AI-Powered Spending Analytics

Thank you for reviewing Student Expense Tracker. Student Expense Tracker is a modern, AI-powered expense management application built specifically for college students to help them track, analyze, and predict their spending habits. Developed as a submission for the RETROD Travel Tech Hackathon 2026, the project transforms traditional expense tracking into an intelligent financial assistant by combining data analytics, interactive visualizations, and machine learning. The application addresses a common problem faced by students—managing daily expenses such as UPI payments, food, travel, mobile recharges, shopping, and miscellaneous spending. Instead of simply recording transactions, it provides meaningful insights into spending behavior, budget management, and future expenditure predictions. Core Features Add expenses with date, amount, category, payment mode, and description. View all transactions in a clean, searchable ledger with summary statistics. Automatically calculate total spending, average spending, and highest spending category. Set and monitor monthly budgets with real-time progress tracking and visual alerts. Filter expenses by month for better financial organization. Export complete expense history as a CSV file. Includes 11 pre-loaded sample expenses for immediate testing without manual data entry. Machine Learning Features The project extends beyond the hackathon requirements by integrating intelligent analytics using scikit-learn. Anomaly Detection: Uses the Isolation Forest algorithm to identify unusual or suspicious spending patterns. Spending Prediction: Employs Linear Regression to forecast spending for the next seven days and estimate projected monthly expenses. Spending Pattern Analysis: Evaluates spending trends by day of the week and weekly activity to identify high and low spending periods. Category Insights: Analyzes category frequency, total expenditure, average transaction value, and spending distribution for deeper financial understanding. Interactive Analytics Dashboard The application provides an intuitive dashboard with interactive visualizations, including: Category-wise pie charts Bar charts for spending comparison Daily spending trend graphs Budget progress meter with color-coded alerts Scatter plots for category analysis Real-time financial summaries and key metrics User Experience The application features a modern dark-themed interface with responsive layouts, glassmorphism-inspired design, and color-coded indicators to provide an engaging and user-friendly experience. The interface is designed to remain simple for beginners while delivering powerful analytical capabilities. Technical Highlights Built using Python, Streamlit, Pandas, Plotly, and scikit-learn. Efficient single-file architecture with modular functions. Graceful handling of optional machine learning dependencies. Clean, maintainable code with documentation, type hints, inline comments, and robust error handling. Testing & Performance The application is optimized for fast execution, typically loading in under two seconds while keeping memory usage below 100 MB. All core hackathon requirements have been implemented and thoroughly tested using the included sample dataset, ensuring that expense management, analytics, budgeting, CSV export, and machine learning insights work as expected. Future Scope The current implementation establishes a strong foundation for future enhancements, including: SQLite/PostgreSQL database integration User authentication and cloud synchronization OCR-based receipt scanning Advanced forecasting models such as LSTM Multi-currency support Savings goal tracking Natural language expense entry Automated financial reports Mobile application support Why This Project Stands Out Successfully implements every required hackathon feature. Goes beyond the problem statement by incorporating practical machine learning models. Provides meaningful financial insights rather than basic expense logging. Includes interactive visualizations for better decision-making. Offers immediate testing through pre-loaded sample data. Designed with scalability and future enhancements in mind. Demo Instructions Run the application using: streamlit run expense_tracker.py No login or account creation is required. The application automatically loads sample expense data, allowing reviewers to explore every feature immediately. Project Demo Video 🎥 Demo Video: https://drive.google.com/file/d/10x91HIlEKvWlH0z82V_4rCu4y_30wBJ8/view?usp=sharing Thank you for taking the time to review Student Expense Tracker. I hope you enjoy exploring the project and its intelligent approach to personal finance management.