DEVELOPMENT OF AN EXPENSE TRACKING MODEL USING LINEAR REGRESSION ALGORITHM

This study presents the development of a predictive model for forecasting monthly expenses and identifying influential spending categories to enhance personal financial planning. Utilizing linear regression as the primary machine learning approach, the model analyzes historical spending data to generate monthly expense predictions and highlight categories with the highest impact on total expenditures. The dataset includes variables such as income, food and household expenses, transportation, clothing, and miscellaneous spending, which are preprocessed and split into training and testing sets to build and validate the model. Key evaluation metrics—Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R²)—are used to assess model performance, indicating a high degree of accuracy and reliability in predictions. Results show that categories such as food and household expenses, and transportation have the most significant influence on overall monthly spending. This project provides a foundation for developing tools to assist users in managing their finances, offering insights into spending patterns and facilitating proactive budgeting strategies based on predictive analytics. The implementation of this model using Python libraries such as scikit-learn, pandas, and matplotlib demonstrates its practicality for real-world applications in personal finance management.