AI-Based Wealth Advisory System using Machine Learning and Predictive Analytics for Personalized Budget Planning
DOI:
https://doi.org/10.15662/IJARCST.2025.0805004Keywords:
Artificial Intelligence, Machine Learning, Predictive Analytics, Wealth Advisory System, Budget Planning, Anomaly Detection, Explainable AIAbstract
Artificial Intelligence (AI) has emerged as a powerful driver of innovation in financial technology (FinTech), enabling predictive analytics, anomaly detection, and automated advisory services. Yet, most personal finance applications remain limited, focusing primarily on reactive expense tracking rather than proactive wealth management. This paper introduces AI Wealth Advisor, an intelligent system designed to deliver personalized budget planning, financial goal setting, and expenditure optimization using machine learning and predictive analytics. The system integrates classification, forecasting, anomaly detection, and explainable AI (XAI) to provide transparent, real-time financial guidance. Through Natural Language Generation (NLG), it translates complex analytics into simple, actionable recommendations, accessible to individuals across diverse literacy levels. A pilot study showed promising results: anomaly detection accuracy of 95%, a 22% improvement in savings, and enhanced financial literacy for 78% of participants. In addition to performance improvements, the system addresses challenges related to privacy, fairness, and user trust. This report details the methodology, research workflow, and results of AI Wealth Advisor, supported by visual analytics. Findings indicate that the system can bridge the gap between advanced financial analytics and practical usability, positioning itself as a scalable digital companion that empowers individuals to achieve sustainable financial well-being.
References
1. Mohammed, A., et al. (2021). “An Enhanced Secure Deep Learning Algorithm for Fraud Detection.” Journal of Computer Science & Technology. https://onlinelibrary.wiley.com/doi/10.1155/2021/6079582
2. Carcillo, F., et al. (2019). “An Ensemble Learning Approach for Anomaly Detection in Credit Card Data with Imbalanced and Overlapped Classes.” Expert Systems with Applications. https://www.sciencedirect.com/science/article/pii/S2214212623002028
3. Zhang, G., et al. (2022). “Time Series Forecasting Using a Hybrid ARIMA and Neural Network Model.” Neurocomputing. https://www.researchgate.net/publication/222735629_Zhang_GP_Time_Series_Forecasting_Using_a_Hybrid_ARIMA_and_Neural_Network_Model_Neurocomputing_50_159-175
4. Makridakis, S., et al. (2018). “Statistical and Machine Learning Forecasting Methods: Concerns and Ways Forward.” International Journal of Forecasting. https://doi.org/10.1016/j.ijforecast.2018.01.001
5. Yang, X., et al. (2023). “The Impact of Artificial Intelligence on Financial Literacy.” Journal of Financial Technology. https://www.researchgate.net/publication/383184105_THE_IMPACT_OF_ARTIFICIAL_INTELLIGENCE_ON_FINANCIAL_LITERACY
6. Bauman, M., et al. (2023). “Deep Reinforcement Learning for Goal-Based Investing Under Regime-Switching.” Proceedings of Machine Learning Research. https://proceedings.mlr.press/v233/bauman24a/bauman24a.pdf
7. Li, L., et al. (2021). “A Contextual-Bandit Approach to Personalized News Article Recommendation.” arXiv. https://arxiv.org/abs/1003.0146
8. Priya, S., et al. (2024). “Explainable AI (XAI) for Trustworthy and Transparent Decision-Making: A Theoretical Framework for AI Interpretability.” Journal of AI Research. https://www.researchgate.net/publication/389783123_Explainable_AI_XAI_for_trustworthy_and_transparent_decision-making_A_theoretical_framework_for_AI_interpretability
9. Ribeiro, M. T., et al. (2016). “Model-Agnostic Explainable Artificial Intelligence Methods.” Knowledge-Based Systems. https://link.springer.com/article/10.1007/s10462-025-11215-9
10. Kury, P., et al. (2025). “Generative AI and Finance: A Multi-level Machine Learning Approach.” SSRN. https://papers.ssrn.com/sol3/Delivery.cfm/5129013.pdf?abstractid=5129013&mirid=1
11. Abadi, M., et al. (2016). “Differential Privacy in Machine Learning.” Communications of the ACM. https://onlinelibrary.wiley.com/doi/10.1155/2021/6079582
12. Barocas, S., et al. (2019). “Fairness and Machine Learning.” Fairness, Accountability, and Transparency in Machine Learning. https://www.sciencedirect.com/science/article/abs/pii/S2542660525002100
13. Lundberg, S., & Lee, S.-I. (2017). “SHAP (SHapley Additive exPlanations).” arXiv. https://link.springer.com/article/10.1007/s10462-025-11215-9
14. Davis, F. D., et al. (1989). “Perceived Usefulness, Perceived Ease of Use, and User Acceptance of Information Technology.” MIS Quarterly. https://www.nature.com/articles/s41599-025-04850-8
15. Goodfellow, I., et al. (2016). “Deep Learning.” MIT Press. https://www.nature.com/articles/s41599-025-04850-8
