Home / Current Issue / Paper 1724558
FINTRACK: An Intelligent Expense Tracking and Behavioural Analysis System
Subject area: Science,Engineering and Technology · Area of research: Machine Learning in Financial Analytics
Abstract
Personal expense tracking applications commonly record transactions but provide limited support for interpreting spending behaviour over time. This paper presents FinTrack, a locally deployable web-based system that combines expense recording, machine-learning-based behavioural classification, trend visualisation, rule-based recommendations, and month-to-month drift alerts. The application is implemented using Python and Streamlit, with SQLite for persistence, Pandas and NumPy for data processing, Scikit-learn for classification, and Matplotlib for visualisation. A Decision Tree classifier uses three features—expense-to-income ratio, savings rate, and number of active spending categories—to assign one of three labels: Saver, Balanced, or Overspender. The model is trained on 360 synthetically generated labelled profiles and evaluated using a stratified 80:20 holdout split. The project report records an accuracy of 97.22% (70 correct predictions from 72 test samples). The system also applies threshold-based alerts for increases in expenditure, declines in savings, and category-level spikes, and provides a dashboard for examining monthly and category-wise patterns. These results demonstrate the technical feasibility of integrating lightweight, interpretable analytics into a personal finance application. However, because the classifier is evaluated on synthetic data generated from rule-based class boundaries, the reported accuracy should not be interpreted as evidence of generalisation to real-world users. Further evaluation on representative real transaction histories is required.
Keywords
personal finance management; expense tracking; behavioural classification; decision tree; synthetic data; spending analysis; drift detection
References
[1] Agrawal R, Gehrke J, Gunopulos D, Raghavan P. Automatic transaction categorization using machine learning. In: Proceedings of the International Conference on Knowledge Discovery and Data Mining; 2015. p. 112–120.
[2] Wang Y, Li X, Zhang J. Automated personal finance categorization using Naive Bayes classification on transaction narratives. Journal of Financial Technology Research. 2018;4(2):45–61.
[3] Sharma A, Kapoor N. Usability study of personal finance applications in the Indian market: Barriers to sustained engagement. International Journal of Human-Computer Studies. 2019;12(1):88–97.
[4] Lessmann S, Baesens B, Seow HV, Thomas LC. Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research. 2015;247(1):124–136.
[5] Koudela P, Novak M, Bartosik L. Behavioral segmentation of personal finance users using supervised machine learning. In: Proceedings of the 14th International Conference on Business Intelligence and Data Mining; 2020. p. 203–212.
[6] Zhang L, Chen H, Wang F. Comparing supervised classifiers for spending behavior prediction: Interpretability versus accuracy. IEEE Access. 2021;9:78342–78356.
[7] Bahnsen AC, Aouada D, Stojanovic A, Ottersten B. Feature engineering strategies for credit card fraud detection. Expert Systems with Applications. 2016;51:134–142.
[8] Jain S, Patel R. The effect of automated spending alerts on financial behavior: A controlled experiment. Behavioral Finance Quarterly. 2019;7(3):34–48.
[9] Few S. Show me the numbers: Designing tables and graphs to enlighten. 2nd ed. Burlingame (CA): Analytics Press; 2012.
[10] Heer J, Bostock M. Crowdsourcing graphical perception: Using Mechanical Turk to assess visualization design. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI); 2010. p. 203–212.
How to cite this paper
@article{1724558,
author = {Tharun Kumaar S D, Lakchan S},
title = {FINTRACK: An Intelligent Expense Tracking and Behavioural Analysis System},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {5},
pages = {258-263},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1724558.pdf},
abstract = {Personal expense tracking applications commonly record transactions but provide limited support for interpreting spending behaviour over time. This paper presents FinTrack, a locally deployable web-based system that combines expense recording, machine-learning-based behavioural classification, trend visualisation, rule-based recommendations, and month-to-month drift alerts. The application is implemented using Python and Streamlit, with SQLite for persistence, Pandas and NumPy for data processing, Scikit-learn for classification, and Matplotlib for visualisation. A Decision Tree classifier uses three features—expense-to-income ratio, savings rate, and number of active spending categories—to assign one of three labels: Saver, Balanced, or Overspender. The model is trained on 360 synthetically generated labelled profiles and evaluated using a stratified 80:20 holdout split. The project report records an accuracy of 97.22% (70 correct predictions from 72 test samples). The system also applies threshold-based alerts for increases in expenditure, declines in savings, and category-level spikes, and provides a dashboard for examining monthly and category-wise patterns. These results demonstrate the technical feasibility of integrating lightweight, interpretable analytics into a personal finance application. However, because the classifier is evaluated on synthetic data generated from rule-based class boundaries, the reported accuracy should not be interpreted as evidence of generalisation to real-world users. Further evaluation on representative real transaction histories is required.},
keywords = {personal finance management; expense tracking; behavioural classification; decision tree; synthetic data; spending analysis; drift detection},
month = {November},
}