Authors : Velkur Dilip; Dr. R. Sathya Janaki

Volume/Issue : Volume 11 - 2026, Issue 7 - July

Google Scholar : https://tinyurl.com/4atxbbyz

Scribd : https://tinyurl.com/4wzsufbf

DOI : https://doi.org/10.38124/ijisrt/26jul842

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Financial management has become increasingly challenging due to the rapid growth of digital payment platforms, multiple banking channels, and continuously changing spending behavior. Traditional expense management systems primarily focus on recording financial transactions without providing intelligent forecasting or transparent recommendations that assist users in making informed financial decisions. The integration of Artificial Intelligence (AI) and Explainable Artificial Intelligence (XAI) has created new opportunities for developing intelligent financial management systems capable of predicting future expenses while maintaining transparency in decision-making. This paper presents FinSenseAI, an Explainable AI-based Personal Finance Recommendation and Expense Prediction System using a Hybrid Machine Learning Framework consisting of Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), and SHapley Additive exPlanations (SHAP). The proposed framework utilizes a real-world financial transaction dataset containing transaction date, expense category, transaction amount, transaction type (Income/Expense), and transaction description. Data preprocessing includes duplicate removal, missing value analysis, categorical encoding, temporal feature extraction, normalization, and feature engineering to improve prediction performance. The XGBoost model efficiently captures nonlinear relationships among structured financial attributes, whereas the LSTM network learns sequential spending behavior from historical transactions. The outputs of both models are combined through a hybrid ensemble strategy to enhance forecasting performance. SHAP is integrated to provide interpretable explanations of model predictions by quantifying the contribution of each feature to the predicted expense. The proposed framework is evaluated using standard regression metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination (R²). Rather than serving as a conventional expense tracker, FinSenseAI provides predictive financial analytics and personalized budgeting recommendations supported by transparent AI explanations. The proposed architecture is scalable and can be extended to integrate banking APIs, mobile applications, cloud deployment, and real-time financial monitoring, making it a promising solution for intelligent personal financial management. The proposed framework was implemented using Python-based machine learning libraries, including Scikitlearn, XGBoost, TensorFlow, and SHAP. The dataset was preprocessed using feature engineering, categorical encoding, and temporal feature extraction. The framework is designed to support intelligent budgeting and transparent financial decisionmaking through explainable artificial intelligence.

Keywords : Personal Finance, Expense Prediction, Explainable Artificial Intelligence, XGBoost, Long Short-Term Memory, SHAP, Hybrid Machine Learning, Financial Forecasting, Budget Recommendation, FinTech.

References :

1. T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794, 2016.
2. S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
3. S. M. Lundberg and S.-I. Lee, "A Unified Approach to Interpreting Model Predictions," Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
4. J. H. Friedman, "Greedy Function Approximation: A Gradient Boosting Machine," Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
5. L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
6. F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
7. M. Abadi et al., "TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems," 2016.
8. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
9. A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd ed., O'Reilly Media, 2022.
10. F. Chollet, Deep Learning with Python, 2nd ed., Manning Publications, 2021.
11. G. James, D. Witten, T. Hastie, and R. Tibshirani, An Introduction to Statistical Learning, 2nd ed., Springer, 2021.
12. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed., Springer, 2009.
13. W. McKinney, Python for Data Analysis, 3rd ed., O'Reilly Media, 2022.
14. S. M. Lundberg, G. G. Erion, and S.-I. Lee, "Consistent Individualized Feature Attribution for Tree Ensembles," 2018.
15. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed., MIT Press, 2018.
16. Y. LeCun, Y. Bengio, and G. Hinton, "Deep Learning," Nature, vol. 521, pp. 436–444, 2015.
17. C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
18. K. P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012.
19. C. C. Aggarwal, Neural Networks and Deep Learning, Springer, 2018.
20. J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed., Morgan Kaufmann, 2012.
21. S. Raschka and V. Mirjalili, Python Machine Learning, 3rd ed., Packt Publishing, 2019.
22. T. M. Mitchell, Machine Learning, McGraw-Hill, 1997.
23. L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proceedings of COMPSTAT, 2010.
24. D. P. Kingma and J. Ba, "Adam: A Method for Stochastic Optimization," International Conference on Learning Representations (ICLR), 2015.
25. D. Silver et al., "Mastering the Game of Go with Deep Neural Networks and Tree Search," Nature, vol. 529, pp. 484–489, 2016.