استخدام خوارزمية Xgboost للتنبؤ بأسعار الإغلاق لسهم شركة Apple

Abstract

The aim of this study was to predict the daily closing prices of Apple Inc. stock using a machine learning model, specifically the XGBoost algorithm, to assist investors to making stock market investment decisions. The study covered the period from January 2, 2020, to July 11, 2024, with a total sample size of 1138 observations. Of these, 911 observations (80% of the total) were used for training, and 227 observations (20% of the total) were used for testing. The XGBoost model was built using the Python programming language, relying on its associated libraries, with the XGBoost library being the most important. The results of this study indicated a high predictive ability of the XGBoost algorithm based on certain performance metrics used in this study.