Forecasting Stock Prices using ARIMA algorithm

Abstract: The stock prediction project presented here aims to develop an interactive application for analysing and forecasting stock prices using historical data. The project utilizes Python's Tkinter for a graphical user interface, enabling users to input National Stock Exchange (NSE) company symbols and fetch stock data from Yahoo Finance. The application retrieves one year of historical stock prices, including closing prices and trading volumes. The project further enhances analysis by incorporating moving averages—50day and 200-day—to provide trend insights. For predictive analytics, the system employs the ARIMA (Auto Regressive Integrated Moving Average) model, a well-established time- series forecasting technique. This model is trained on the stock’s closing prices and generates future price predictions for the next 30 days. The results are visually represented through Matplotlib, with historical prices, moving averages, trading volumes, and forecasted prices displayed on interactive charts. This project is particularly useful for investors, traders, and financial analysts seeking to understand stock trends and predict potential future movements. The intuitive interface allows users to seamlessly interact with stock data, view market trends, and make data-driven decisions. The integration of real-time data fetching, statistical modeling, and visualization makes this application a powerful tool for stock market analysis.