Even-odd crossover: a new crossover operator for improving the accuracy of students’ performance prediction

Abstract

Prediction using machine learning has evolved due to its impact on providing valuable and intuitive feedback. It has covered a wide range of areas for predicting student’ performance. Instructors can track student’s dropout in a particular course at an early stage and try to improve students’ performance. The problem of students’ future performance prediction using advanced statistics and machine learning is a hard problem due to the imbalanced nature of the student data where the number of students who passed the exam is generally much higher than the number of students who failed the exam. This paper proposes a new type of crossover operator called Even-Odd crossover to generate new instances into the minority class to handle the imbalanced data problem. The experiments are implemented using three machine learning (ML) algorithms: random forest (RF), support vector machines (SVM), and K-Nearest-Neighbor (KNN) to ensure the efficiency of the proposed technique. The performance of the classifiers is evaluated using several performance measures. The efficient ability of the proposed method on solving the imbalance problem is proved by performing the experiments on 22 real-world datasets from different fields and four students’ datasets. The proposed Even-Odd crossover shows superior performance compared to state-of-the-art resampling techniques.