InvestMate: A Hybrid AI-Driven Financial Chatbot for Personalized Stock Predictions and Investor Education
In order to assist new traders in making wellinformed inventory investment decisions, this paper provides InvestMate, a sophisticated conversational chatbot pushed via artificial intelligence. In contrast to conventional economic consulting systems, InvestMate meets the getting to know and selection-making needs of newbie traders by using fusing interactive education with individualized advice. In order to offer personalized stock guidelines which are consistent with each person’s monetary targets and possibilities, the chatbot algorithms for short-and medium-term predictions. This combination enables the chatbot to provide consistent, datadriven insights across varying collects user inputs consisting of funding quantity, target term, and threat tolerance. To achieve robust prediction accuracy, InvestMate employs a dual-model approach using Long Short-Term Memory (LSTM) networks for long-term forecasting and Random Forest investment horizons, whether the user is planning for a few months or several years. The two-model strategy ensures a balance between capturing historical patterns with LSTM’s sequential memory capacity and leveraging the robustness of ensemble methods, as found in the Random Forest model, for more immediate, shorter-term analysis. In addition to offering inventory tips, InvestMate actively promotes economic literacy by means of teaching customers in key ideas like marketplace indicators, threat control, diversification, and fundamental studies. The chatbot’s prediction models are trained on an extensive dataset containing 1,962 CSV files of stock data from the National Stock Exchange (NSE), encompassing stocks up to March 15, 2024. This comprehensive dataset allows InvestMate to learn from diverse market conditions and adapt its recommendations to current trends and patterns, enhancing reliability and relevance. In addition to helping new investors make better investment decisions, InvestMate also acts as a friendly investment coach, bridging knowledge gaps for people unfamiliar with the stock market complexity by providing an interactive, educational tool that builds confidence and practical knowledge for inexperienced investors.
Authors
- Neha Garg (ORCID: https://orcid.org/0000-0003-3806-6964)
- Keshav Sharma (ORCID: https://orcid.org/0009-0005-8529-9500)
- Ayush Raghav
- Nitish Adhana
Institutions
- Manav Rachna International Institute of Research and Studies (IN)
Publication Details
- Published
- 2024-11-28
- DOI
- https://doi.org/10.1109/icaiccit64383.2024.10912150
- Primary Topic
- Stock Market Forecasting Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00