Stock market Price Prediction Using Machine Learning and Deep learning

Abstract

This project presents a dynamic Stock Market Price Prediction Website that utilizes Machine Learning (ML) and Deep Learning (DL) techniques to forecast future stock prices based on real-time and historical data. The system is designed with a full-stack architecture, featuring a responsive frontend using HTML, CSS, and Bootstrap, and a robust backend powered by Python (Django) with data storage handled through SQLite. For data acquisition, the project integrates the Yfinance API to fetch live and historical stock market data and uses BeautifulSoup to scrape the latest financial news articles. The collected data is preprocessed using Pandas and Numpy, and predictive models are built using Scikit-Learn along with deep learning frameworks. The system implements two advanced algorithms: Long Short-Term Memory (LSTM) networks, which are highly effective for time-series forecasting, and Convolutional Neural Networks (CNN), which enhance feature extraction from financial data. These models work together to predict stock price trends with improved accuracy. In addition to prediction capabilities, the website features a live stock news section and a portfolio management tool that allows users to track and analyze selected stocks. The user-friendly interface and real-time functionalities make it suitable for investors, students, and financial analysts. Overall, this project demonstrates the practical application of ML and DL in financial forecasting, combining data science, web development, and automation to build a comprehensive and interactive stock analysis platform.