Introduction. Research in the field of educational data mining, also known as Educational Data Mining (EDM), focuses on identifying hidden patterns in various educational situations. This study developed a model that predicts student performance based on their scores in the Surgical Nursing course using two machine learning methods: Decision Tree and Random Forest. Both selected models demonstrate high accuracy in predicting student performance and can be used for this purpose. Purpose of the study. To develop models for predicting student performance for the next academic year, based on the disciplinary rating of the previous academic year (the main professional educational program of higher education is the undergraduate program in the field of study 34.03.01 Nursing (general profile)). Materials and methods of research. To predict the performance of 3rd year students (2022-2023 academic year) in the next academic year, the discipline “Nursing in Surgery” and student ratings from electronic journals of the Department of Nursing were taken. The students’ date of birth was taken from the personal account of the University information system (IS) teacher in the “Students” section and converted to the age of the students. The sample size was 822 students. Data were analyzed using RapidMiner software (Altair). To predict academic performance, several machine learning methods were used - “Decision Tree”, “Random Forest”. Results and discussions. For statistical data processing, we used the RapidMiner program and the “Statistica” operator. We used the Decision Tree machine learning method to predict student performance for the next academic year. To evaluate the performance of the model, we used the mean square error (MSE), which was 2.006. The correlation coefficient shows how much the independent variables explain the variability of the resulting indicator. In our model, the correlation coefficient was 0.993, which means that the predicted values of the disciplinary ranking are highly consistent with the actual values in the discipline of Surgical Nursing. The mean predicted score was 64.5 ± 23.9. We also used the Random Forest machine learning method to predict academic performance. Random Forest uses an ensemble of decision trees. The accuracy of this model was 90.5%. The resulting performance predictions will allow us to identify students at potential risk of failure in their studies and develop a support system that will help correct the current situation of students. Conclusion. The selected models for predicting the performance of students in the discipline “Nursing in Surgery”, the regression model “Decision Tree” and “Random Forest” showed excellent accuracy and can be used to predict the performance of students.