Comparative Study of Machine Learning Algorithms for Stock Market Prediction and Analysis of Correlation Between Nifty 50 and Global Indices

Abstract

The volatile nature of the stock market presents significant challenges for investors and individuals like them. Economic indicators, geopolitical events, and market sentiment influence the prediction of stock prices key sentiment. In recent years,
machine learning algorithms have emerged as powerful tools for stock market prediction due to their ability to analyze large datasets and identify complex patterns. This research aims to conduct a comparative study of machine learning algorithms to estimate their effectiveness in predicting stock market trends, focusing on the Nifty 50 index.
This research will explore several machine-learning algorithms, including, but not limited to, linear regression, decision trees, random forests, support vector machines, and artificial neural networks. We will utilize historical stock market data, which
encompasses a range of features like price, volume, and volatility, to train and evaluate the performance of these algorithms. Through accurate experimentation and analysis, the research will recognize the best-fit algorithm or combination of algorithms for error-less stock market prediction.
Furthermore, the research will investigate the correlation between the Nifty 50 index and key global indices, metals, and crude oil prices. Understanding these correlations is essential for investors to make informed decisions and manage risks effectively. Investors can better anticipate market motion by understanding the interrelatedness of different financial markets and commodities through statistical methods and data visualization techniques.
The findings of this research carry important implications for investors, financial analysts, and policymakers, providing them with valuable information about volatile and uncertain stock markets and their relationship with global economic indicators. This
study seeks to enhance the accuracy and dependability of stock market prediction and risk management models by utilizing modern machine learning techniques and statistical analysis.
Here, I have created a stock analysis model. Using a Python function, I downloaded the dataset from Yahoo Finance, which included data from the past 20 years as of today. In our model, the user can input any listed stock, including commodities.
It first analyzes the stock and then predicts its future value. We are employing various machine learning algorithms, such as linear regression, decision trees, random forests, neural networks, and support vector machines. We compare their performance
using parameters such as R-square, RMSE, and MAE, and then make a final decision on which one is the best for predicting the stock market.