The use of ensemble machine learning models to analyze factors affecting schoolchildren academic performance in distance learning

In the COVID-19 pandemic, the education system has faced unprecedented challenges requiring adaptation and implementation of new teaching methods and data analysis. This article discusses the use of ensemble machine learning models to predict student learning activity in distance education. The data on student engagement collected through the questionnaire is analyzed, and forecasting models are built based on these data. The study revealed that the combination of random forest (RF), k-nearest neighbor (KNN) algorithms and the gradient bootstrap method (XGBoost) demonstrates high accuracy and reliability of forecasts. The results of the study show that ensemble models can be effectively used to analyze educational data and make informed decisions in crisis situations. The research uses data from a survey conducted by the National Academy of Education named after I. Altynsarin in 2020 with the participation of 39,450 students from schools in the Republic of Kazakhstan.