International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 12 Issue: 12 | Dec 2025
p-ISSN: 2395-0072
www.irjet.net
AI-POWERED PERSONAL FINANCE TRACKER USING BEHAVIORAL PATTERN ANALYSIS LakshmiKishore.M1, Mrs.Bhuvaneswari.B2 1PG Student, Department Of Computer Applications, Jaya College of Arts and Science, Thiruninravur, Tamilnadu,
India
2Assistant Professor Department Of Computer Applications, Jaya College of Arts and Science, Thiruninravur,
Tamilnadu, India -------------------------------------------------------------------------***------------------------------------------------------------------------
Abstract - In the modern digital era, individuals conduct
3. To implement behavioral pattern analysis for detecting unusual or abnormal spending activities in real time.
hundreds of financial transactions every month through mobile wallets, banking apps, and online payments. While many applications track these transactions, they rarely provide meaningful insights into spending behaviour or predictive guidance for budgeting. This paper proposes an AIpowered personal finance tracker that uses behavioural pattern analysis and machine learning algorithms to predict future expenses and detect unusual spending habits. The system is developed using Python and Flask, integrated with a MySQL database for storing transaction data. Machine learning models such as Random Forest and LSTM are applied to analyze user patterns and forecast monthly spending. Experimental results show that the proposed system improves financial awareness and helps users maintain better control over their expenditure compared to traditional static trackers.
4. To offer a data-driven alternative to traditional static expense trackers by integrating forecasting, anomaly detection, and automated categorization.
2. LITERATURE REVIEW Priya Sharma et al. [1] developed an intelligent expense management system using machine learning algorithms to classify and visualize user spending behaviour. Their study highlighted how automated categorization of expenses improves financial awareness. Ankit Kumar and R. Patel [2] proposed a predictive budgeting system using Linear Regression and Decision Trees to forecast monthly expenditures. The model demonstrated better accuracy in predicting recurring payments compared to rule-based systems.
Keywords: Machine Learning, Expense Prediction, Behavioral Analysis
1. INTRODUCTION
S. Banerjee et al. [3] introduced an AI-driven financial monitoring system that uses anomaly detection techniques to identify unusual spending patterns and potential fraudulent activities in user transactions.
In today’s digital world, individuals perform numerous transactions through UPI wallets, online banking, and ecommerce platforms. Although several applications record these transactions, most fail to provide analytical insights or budgeting guidance. Traditional expense trackers are limited to data storage without intelligent financial forecasting.
Finally, J. Zhang et al. [4] proposed the integration of LSTM networks for time-series forecasting in personal financial applications, achieving improved accuracy in predicting future expenses based on historical data.
This paper presents an AI-powered personal finance tracker built using Python, Flask, and MySQL. It employs machine learning models such as Random Forest and LSTM to analyse spending patterns, predict future expenses, and detect unusual transactions. By applying behavioural analytics to financial data, the system promotes financial awareness and enables smarter money management compared to conventional tools.
These studies collectively emphasize that applying machine learning techniques such as Random Forest and LSTM can significantly enhance the functionality of expense trackers by enabling predictive analysis and personalized recommendations.
3. METHODOLOGY
Main Objectives:
3.1 Existing System
1. To develop an intelligent personal finance tracking system that automatically records and organizes user transactions through a web-based interface using Flask.
Traditional expense trackers primarily function as manual recording tools where users enter their daily income and expenditure data. These systems usually provide basic statistical summaries, pie charts, or bar graphs without offering any predictive insights or personalized recommendations.
2. To apply machine learning models (Random Forest & LSTM) for analyzing spending patterns and predicting future monthly expenses.
© 2025, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 64