The rapid expansion of global financial markets has produced an exponential growth in transactional and historical data, making automated analysis and prediction of stock price movements increasingly important for investors, analysts and institutions. This paper presents an AI-Driven Stock Market Analysis Platform that integrates classical statistical methods, machine learning and deep learning into a unified web-based application for stock price forecasting and trend analysis. The proposed system supports four predictive models -Linear Regression, Long Short-Term Memory (LSTM) networks, Autoregressive Integrated Moving Average (ARIMA) and an Ensemble combining Linear Regression and ARIMAoperating on historical Open-High-Low-Close-Volume (OHLCV) data retrieved through the yfinance library. The raw data is enriched with technical indicators including Simple and Exponential Moving Averages, MACD, RSI and volatility, which capture market trend and momentum and improve model performance. The backend is implemented in Python using the FastAPI framework, exposing high-performance REST endpoints for stock information retrieval, historical data, singlemodel prediction and side-by-side model comparison. The frontend is a responsive single-page application built with HTML, CSS and JavaScript that visualizes price trends and predictions through Chart.js. For each request the system returns the predicted price, trend direction, confidence score and evaluation metrics including Mean Absolute Error and R-squared. The platform demonstrates how modern machine-learning techniques can be integrated into an accessible, cost-effective and reproducible solution for financial analysis, lowering the barrier to data-driven decision-making for retail investors, academic researchers and finance professionals alike..
Kumar et al. (Thu,) studied this question.