Determinants and Prediction of Secondary Students Performance in Mathematics in Portugal Using Machine Learning

Abstract

Mathematics brings order and prevents chaos in our lives. Power of reasoning, inventiveness, abstract or spatial thinking, critical thinking, problem-solving abilities, and even excellent communication skills are some of the attributes that mathematics fosters. The purpose of this research is to identify the factors that impact students' mathematics performance. Simultaneously, this study tries to predict student's mathematics performance. The secondary information was gathered from https://archive.ics.uci.edu/ml/datasets/student+performance#. This study uses a variety of methodologies such as percentage distribution, association tests, association rule mining, Decision tree, Random Forest, Support Vector Machine, Naive Bayes, K-Nearest-Neighbors, Linear Discriminant Analysis, Neural Network, and Logistic Regression. Students whose father's education is higher, mother's education is higher, mothers' occupation services, who rarely go out with friends, and who did not fail the previous class have considerably better mathematics performance. Students whose father has a primary education, who spend a lot of time with friends, drink alcohol during the workday, and live in rural areas have poor mathematics performance. Furthermore, in this case, the best classifier for prediction is a Neural Network. Therefore, the performance of students in mathematics depends on the characteristics of the students as well as the characteristics of their parents and place of residence. The government and other NGOs must step forward to educate the country's people about these critical factors.

Keywords: Determinant, Prediction, Student, Performance, Machine, Learning.

DOI: 10.7176/CEIS/13-5-03

Publication date:October 31^st 2022