PREDICTING COURSE GRADES OF STUDENTS’ ACADEMICPERFORMANCE USING THE LIGHTGBM REGRESSOR

In the modern world, using all available opportunities andtechnologies, special attention should be paid to the development of theeducation system of students, since education serves as the basis for thedevelopment of the future generation. Nowadays, thanks to the use of availableArtificial Intelligence methods, it is possible to predict various events, anomaliesor other important things. With the help of machine learning, it is possible topredict at an early stage of a student's education whether he will finish the coursesuccessfully or not. In this study, it is proposed to predict the final score whichstudent will receive at the end of the course using a number of predictors as anassessment for the first quiz and 3 types of tasks using the LightGBM regressor,which is a high-performance algorithm with gradient boosting. The results ofusing the LGBM regressor using GridSearchCV allowed to determine the bestsettings of hyperparameters from three selected tree-like boosting methods:'dart', 'gbdt', 'goss'. The GOSS method was determined to be the best of the threemethods listed with an estimate of R2 score in 0.81, which is 0.24 more than theR2 score of the Linear Regression forecast of – (0.57).