Prediction of Senior High School Students’ Performance in a State University: An Educational Data Mining Approach

Abstract

The study was conducted to predict the performance of the senior high school students in one state university using machine learning algorithms. Data mining process was followed to develop a model for predicting the students’ performance. The 4-year records of senior high school students of Laguna State Polytechnic University-Los Baños was gathered and used in the model development through well-known machine learning algorithms such as decision tree, naïve bayes, random forest, neural network and linear regression. Upon the development of the models, it is found in this study that naïve bayes performs well against the remaining algorithms and neural networks also shown a promising result in predicting student performance. The study also found that senior high school students have a high chance of not performing well upon entering the school based on the prediction of naïve bayes showing a high probability of satisfactory rating in Grade 11-1st semester applied subjects. Moreover, among the strands offered in Laguna State Polytechnic University-Los Baños, Accountancy, Business and Management students predicted to have the highest chance of having outstanding performance while Information and Communications Technology students predicted to have a high chance of satisfactory.