What does this research mean for the field?

Integrating a two-layer Long Short-Term Memory (LSTM) network with an autonomous AI agent via the Model Context Protocol enables highly accurate real-time stock market forecasting and natural-language-driven financial queries. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This work aims to develop a real-time stock market analysis platform that integrates deep learning and autonomous AI to enhance prediction accuracy.

June 19, 2026Open Access

Real Time Stock Market Analysis Using Agentic AI

Key Points

This work aims to develop a real-time stock market analysis platform that integrates deep learning and autonomous AI to enhance prediction accuracy.
Developed an AI-driven stock market analysis platform using deep learning forecasting.
Analyzed both live and historical Open-High-Low-Volume (OHLCV) data from AlphaVantage API.
Trained a two-layer Long Short-Term Memory (LSTM) network in TensorFlow with feature-augmented sequences.
Achieved an intraday predictive fidelity of 1.85.
Attained a Mean Absolute Error of 1.42.
Exhibited a coefficient of determination (R²) of 0.92 for regression analysis.

Abstract

AbstractModern financial markets have produced vast amounts of data, the complexity of which is way beyond theability of traditional statistical methods to handle. This paper is a stock-market analysis platform in realtime, which combines both deep learning forecasting and an autonomous AI agent. The system will retrieveopen-high-low-volume live data and historical Open-High-Low-Volume (OHLCV) data in the AlphaVantage API and augments it with feature-engineering operations to generate four technical indicators:Relative Strength Index (RSI), Average True Range (ATR), Moving Average Convergence Divergence(MACD), and Money Flow Index (MFI). In this study, the feature-augmented sequences are used to traina two-layer Long Short-Term Memory (LSTM) network using the TensorFlow. Another unique additionof the work is that an Ollama-driven AI agent is integrated, which interacts with the predictive engine viathe Model Context Protocol (MCP), allowing fully conversational and natural-language-driven stockqueries. The entire pipeline gets surfaced using Flask web interface that can be accessed by technical andnon technical user. Analysis of the intraday data of Apple Inc. (AAPL) provides an intraday predictivefidelity of 1.85, the Mean Absolute Error of 1.42, and the coefficient of the square of the regression, R2, of0.92. It has a modular and extendable architecture that provides a practical base to next-generation AI-basedfinancial decision-support systems.

Real Time Stock Market Analysis Using Agentic AI

Key Points

Abstract

Cite This Study