Predictive analysis of student enrolment in secondary schools

Abstract

In research to determine the degree of interest in enrolling students in certain high schools, predictive analysis and comparison models are rarely used when classifying and processing different data. All this leads to large fluctuations in enrolment in secondary schools, where certain schools are unable to enrol numerous students who show an interest in a particular field. On the other hand, students lose interest in certain schools, which leads to the discontinuation of certain courses necessary for the needs of today's labour market. Institutions responsible for organizing the educational process do not sufficiently compare and connect teaching and non-teaching activities when analysing the talents and interests of elementary school students from different fields. The goal of this work is to predict the enrolment of students in secondary schools, using the classifiers of programming languages, based on the results that students express during regular classes in elementary schools.The results show that the accuracy of the data during the training of the Random Forest predictor is 52%, while in Wolfram Alpha it is 62%