The transition from “Income and Expense Tracker” to “Expense Tracker Management System” marks a strategic evolution in financial management tools. This shift underscores a more focused approach towards efficiently tracking and managing expenses. While the former emphasized both income and expenses, the latter places a heightened emphasis on expense management specifically. This refined system aims to streamline expense tracking processes, offering users a robust platform to meticulously monitor and analyze their spending habits. Through customizable features, intuitive interfaces, and comprehensive reporting functional-ities, the “Expense Tracker Management System” empowers users to take full control of their finances, fostering greater financial awareness and facilitating smarter spending decisions which makes it better than the existing state-of-the-art. The article also emphasizes predicting future expenses based on prior experience of the user, using machine learning techniques. Different machine learning techniques are used for prediction purposes such as multi-layer perceptron, extreme gradient boosting, support vector machine and ensemble techniques such as bagging, boosting. Extreme Boost (XGBoost) outperforms other individual models with highest R-square value and voting ensemble regressor outperforms ensemble techniques with highest R-square value of 78.11% and lowest relative absolute error of 0.6121.