Published Paper Details:

By utilising machine learning methods, notably k-Nearest Neighbours (KNN) and XGBoost, this paper gives a complete analysis on the utilisation of these algorithms for the purpose of anticipating trends in the stock market. The purpose of this study is to determine whether or not these algorithms are effective and accurate in predicting stock values based on historical data. In this particular investigation, the dataset that was utilised is comprised of stock market data that was gathered from Yahoo Finance. This dataset includes characteristics such as closing prices, trading volume, and high-low percentage changes. In terms of predicting trends in the stock market, the experimental findings indicate the performance of the KNN and XGBoost models, with the KNN model achieving an accuracy of 96% and the XGBoost model achieving an accuracy of 98%. Both algorithms appear to have promising skills in capturing patterns and trends in stock market data, which highlights their potential for practical applications in investment decision-making and financial analysis. The findings imply that both algorithms exhibit intriguing possibilities in this regard.