FinSenseAI: An Explainable AI-Based Personal Finance Recommendation and Expense Prediction System Using Hybrid Machine Learning Models
International Journal of Innovative Science and Research Technology · 29.07.2026 · 1637
DOI: 10.38124/ijisrt/26jul842 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 29.07.2026. Verfasst von Velkur Dilip und 1 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Dilip, V., & Janaki, R. S. (2026). FinSenseAI: An Explainable AI-Based Personal Finance Recommendation and Expense Prediction System Using Hybrid Machine Learning Models. International Journal of Innovative Science and Research Technology, 1637. https://doi.org/10.38124/ijisrt/26jul842
Vancouver
Dilip V, Janaki RS. FinSenseAI: An Explainable AI-Based Personal Finance Recommendation and Expense Prediction System Using Hybrid Machine Learning Models. International Journal of Innovative Science and Research Technology. 2026:1637. doi:10.38124/ijisrt/26jul842
BibTeX
@article{Dilip2026,
author = {Dilip, Velkur and Janaki, R. Sathya},
title = {FinSenseAI: An Explainable AI-Based Personal Finance Recommendation and Expense Prediction System Using Hybrid Machine Learning Models},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {1637},
doi = {10.38124/ijisrt/26jul842}
}
EUVIMED