Stock Market Trends Analysis using Extreme Gradient Boosting (XGBoost)
Results show that the XGBOOST model is efficient in generating future stock prices and performs with a mean squared error of 0.004, mean absolute error of 0.014 and R2 score of 0.995.
Abstract
The stock market is an option for investment and trading. The market volatility and a wide range of other dependent and independent elements that affect the market value of a particular stock make it challenging to anticipate future values. These characteristics make it extremely difficult for any stock market expert to accurately forecast the market's growth and decline. Stock market predictors help determine future stock prices by taking the previous year's data into account. The prediction is done by the various machine learning models. This paper focuses on forecasting future stock values. using various best machine learning algorithms: k-Nearest Neighbors (KNN), Ada Boost, Support Vector Machine (SVM), Random Forest (RF), and XGBoost. The performance is analyzed using the MSE. Results show that the XGBOOST model is efficient in generating future stock prices and performs with a mean squared error of 0.004, mean absolute error of 0.014 and R2 score of 0.995.