FInsightAI: An AI-Powered Predictive Financial Intelligence Mobile Application — A Comprehensive Literature Review

Wankhade, Siddhant; Patankar, Joel; Ansari, Mohammad Aatir Fawad

doi:https://doi.org/10.55041/ijcope.v2i9.173

Volume 02, Issue 9

Published on: September 2026

FINSIGHTAI: AN AI-POWERED PREDICTIVE FINANCIAL INTELLIGENCE MOBILE APPLICATION — A COMPREHENSIVE LITERATURE REVIEW

Siddhant Wankhade Joel Patankar Mohammad Aatir Fawad Ansari

Prof. Shivani Jagtap

Dept. of AIML, GNIT, Nagpur, India

DOI:https://doi.org/10.55041/ijcope.v2i9.173

Article Status

Plagiarism Passed Peer Reviewed Open Access

Available Documents

Download PDF Review Report

Abstract

Traditional Personal Finance Management (PFM) applications are passive tools that rely on manual data entry, produce static reports, and offer no forward-looking financial intelligence. A newer wave of AI-powered tools introduced Large Language Model (LLM) wrappers, but these suffer from a critical flaw: mathematical hallucinations, where the model generates confident but numerically incorrect financial figures. This paper presents FInsightAI, a native Android mobile application built with React Native and Firebase that directly addresses both problems. FInsightAI automatically captures transaction data via Android SMS broadcast listeners, eliminating all manual entry. It processes this data through a three-tier auto-categorization engine and a deterministic data science backend comprising Holt-Winters Triple Exponential Smoothing for 12-to-36 month cash flow forecasting, Unsupervised Dynamic Z-Score anomaly detection, and Gaussian Kernel Density Estimation (KDE) for peer cohort benchmarking. A Zod schema validation layer ensures the OpenAI GPT-4o-mini advisory engine receives only verified numerical facts, guaranteeing zero mathematical hallucinations. A gap analysis of 2023-2026 literature confirms that no prior work unifies all these components in a single production-grade native mobile framework.

Keywords— Anomaly Detection; Cohort Benchmarking; Financial Intelligence; Grounded AI; Holt-Winters Smoothing; Kernel Density Estimation; Personal Finance Management; React Native.

How to Cite this Paper

Wankhade, S., Patankar, J. & Ansari, M. A. F. (2026). FInsightAI: An AI-Powered Predictive Financial Intelligence Mobile Application — A Comprehensive Literature Review. International Journal of Creative and Open Research in Engineering and Management, <i>02</i>(9), 1-9. https://doi.org/10.55041/ijcope.v2i9.173

Wankhade, Siddhant, et al.. "FInsightAI: An AI-Powered Predictive Financial Intelligence Mobile Application — A Comprehensive Literature Review." International Journal of Creative and Open Research in Engineering and Management, vol. 02, no. 9, 2026, pp. 1-9. doi:https://doi.org/10.55041/ijcope.v2i9.173.

Wankhade, Siddhant,Joel Patankar, and Mohammad Ansari. "FInsightAI: An AI-Powered Predictive Financial Intelligence Mobile Application — A Comprehensive Literature Review." International Journal of Creative and Open Research in Engineering and Management 02, no. 9 (2026): 1-9. https://doi.org/https://doi.org/10.55041/ijcope.v2i9.173.

Search & Index

References

National Payments Corporation of India (NPCI), “UPI Product Statistics,” NPCI Annual Report, 2024. [Online]. Available: https://www.npci.org.in/what-we-do/upi/upi-ecosy stem-statistics.

I. R. Uyanahewa et al., “The Future of Personal Finance Management: A Machine Learning-Driven Approach for Predictive Analysis and Efficient Expense Tracking,” in Proc. IEEE Int. Conf. Emerging Technology (INCET), 2023, pp. 1–6.

Vasquez, L. Chen, and K. Taylor, “Hallucination Mitigation in AI Wealth Tools,” ACM Journal of Financial Technology, vol. 4, no. 3, pp. 89–102, 2025.

Khan, “Leveraging Machine Learning for Predictive Budgeting and Anomaly Detection in Personal Finance,” ResearchGate, Jan. 2025.

Naminas et al., “Mitigating LLM Hallucinations: A Comprehensive Review of Techniques and Architectures,” Preprints.org, May 2025. doi: 10.20944/preprints202505.1955.

Patel, “Real-time Transaction Ingestion and Asynchronous Behavior Discovery,” in Proc. International Fintech Symposium, 2026, pp. 210–224.

Kumar and A. Sharma, “Predictive Hybrid Mobile Architectures in Fintech,” IEEE Software Systems, vol. 22, no. 1, pp. 45–58, 2025.

SmartSpend, “A Unified AI-Powered Personal Finance Dashboard Integrating Fraud Detection, Spending Forecasting and Budget Recommendation,” in Proc. IEEE Conf., 2026. doi: 10.1109/11569599.

C. Holt, “Forecasting Seasonals and Trends by Exponentially Weighted Moving Averages,” International Journal of Forecasting, vol. 20, no. 1, pp. 5–10, 2004.

IJEDR, “AI Powered Personal Finance Tracker with Dashboard and Anomaly Detection,” Int. Electrical and Electronics Research, vol. 14, no. 2, Apr. 2026.

Ethical Compliance & Review Process

•All submissions are screened under plagiarism detection.
•Review follows editorial policy.
•Authors retain copyright.
•Peer Review Type: Double-Blind Peer Review
•Published on: Sep 23 2026

CCBYNC

This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. You are free to share and adapt this work for non-commercial purposes with proper attribution.

View License

Back to Volume 02, Issue 9 View All Issues Next Article

← Previous Article

Explainable AI in Supply Chain Management: Opportunities and Research Challenges

Next Article →

Five Landscapes, One Civilization: Rethinking the History of Ancient Tamilakam Through Tinai