Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69241
Volume:
10 |
11 |
Nov 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Artificial Intelligence and Data Science
All India Shri Shivaji Memorial Society's Institute of Information Technology
Artificial Intelligence and Data Science
All India Shri Shivaji Memorial Society's Institute of Information Technology
Artificial Intelligence and Data Science
All India Shri Shivaji Memorial Society's Institute of Information Technology
Artificial Intelligence and Data Science
All India Shri Shivaji Memorial Society's Institute of Information Technology
Financial decision-making requires individuals to analyse income, expenses, savings, loans and goals together, yet most personal finance applications only record transactions and display dashboards, leaving interpretation to the user. This paper presents FINTRACK, an Agentic AI-based financial decision support system that interprets natural-language financial queries, decomposes them into sub-tasks, invokes deterministic financial tools and generates personalized, explainable recommendations. The architecture combines a Large Language Model (LLM) planning agent with a tool-calling layer for budget analysis, savings projection, EMI computation, goal-based planning and scenario comparison, followed by a recommendation agent and an explanation layer that exposes the factors and calculations behind each answer. The methodology covers data collection, preprocessing, financial analysis, agent development, recommendation generation, explainability and evaluation, and is implemented with Python, FastAPI, LangChain/LangGraph and a web interface. Evaluation is planned on recommendation accuracy, response quality, usability, consistency and reliability. The system is designed as a decision-support tool and not as a substitute for regulated financial advice, and it supports UN Sustainable Development Goal 8 by improving financial literacy and savings behaviour.
KEYWORDS
This paper presented FINTRACK, an intelligent system that combines financial analytics, generative AI and autonomous agent-based workflows to help users make informed financial decisions. Instead of merely displaying financial data, the system understands user goals, analyses relevant information, performs multi-step reasoning, compares alternatives and provides personalized, explainable recommendations, while keeping numerical computation in deterministic tools. Future work includes integration with bank APIs and digital wallets, real-time transaction analysis, advanced predictive financial models, multi-agent financial planning, voice-based interaction, real-time market information where legally and technically appropriate, personalized risk profiling, automated financial reports, reinforcement learning for planning strategies, tax- and retirement-planning modules, a mobile application, and extension to small businesses.
1. J. Lee, N. Stevens, S. C. Han, M. Song, “A Survey of Large Language Models in Finance (FinLLMs),” 2024. 2. Y. Yu et al., “FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making,” 2024. 3. A. Kim, M. Muhn, V. Nikolaev, “Financial Statement Analysis with Large Language Models,” 2024. 4. P. Saha et al., “Large Language Model Agents for Investment Management: Foundations, Benchmarks, and Research Frontiers,” ACM ICAIF, 2025. 5. “Gen-Plan: An Automated Framework for Generalized Planning in Finance Agent,” IEEE, 2025. 6. “Structured Agentic Workflows for Financial Time-Series Modelling with LLMs and Reflective Feedback,” ACM ICAIF, 2025. 7. L. Gupta, S. Kumar, “The Rise of Intelligent Finance: AI in Financial Planning and Financial Literacy,” 2025.
Publication Date
11/20/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
0
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...