Time Series Prediction: Comparative Study of ML Models in the Stock Market

Abstract

Analyzing the Stock Market is a perpetual process and hard to grasp, especially for newcomers looking to invest in the market. This paper will be useful for novice investors to learn to invest in the stock market based on various factors that dictate prices. The paper’s target is to create a program that analyses previous stock data of companies. This also includes identifying factors affecting the share market. We generate the patterns from large data sets of data of the stock market and predict an approximate value of share price. The stock market can have a significant impact on individuals and the economy as a whole. Therefore, accurately predicting stock trends can minimize loss risk and maximize profit. The primary objective of this paper is to generate an approximate forecasting output and a general idea of future values by generating a pattern from historical data. The scope of this paper extends to model a suggestion tool based on ARIMA, XGBoost, and LSTM and give critical insights into their relative advantages and disadvantages, finally determining the best tool for forecasting the trend or even the future. The trend chart will adequately guide all prospective investors. We have analyzed data from the stock market collected from Yahoo Finance. The performance of the models was evaluated using metrics such as MSE, MAE, RMSE, and MAPE. During our trials, we found XGBoost to perform the best with an accuracy of 98.92%.

Comparing Machine Learning Methods—SVR, XGBoost, LSTM, and MLP— For Forecasting the Moroccan Stock Market

“…The LSTM model proved to have the highest accuracy and best model fit. In [13], the authors compared performance measures such as MSE, MAE, RMSE, and MAPE to forecast stock market trends based on Auto-Regressive Integrated Moving Average (ARIMA), XGBoost, and LSTM. Their tests found that XGBoost performed the best.…”