Enhancing Education and Teaching Management Through Data Mining and Support Vector Machine Algorithm

Introduction

In the realm of education, the ability to predict student performance and evaluate learning ability is of paramount importance for educators, administrators, and policymakers. By understanding and anticipating students' academic achievements and learning capabilities, educational institutions can tailor interventions, optimize instructional strategies, and ultimately enhance student outcomes (Shuo & Ming, 2022; Lakshmanna et al., 2022). The integration of machine learning algorithms, such as support vector machines (SVM) and teaching-learning-based optimization (TLBO), offers a promising avenue for improving the accuracy and efficiency of student performance prediction and learning ability evaluation in educational environments. The primary objective of this study is to investigate the effectiveness of the SVM+TLBO approach in predicting student performance and learning ability in educational settings. Specifically, the study aims to address the following research questions:

• •

  How does the SVM+TLBO approach compare to existing methods in predicting student performance?

• •

  What is the predictive capability of the SVM+TLBO approach in evaluating learning ability?

• •

  How can the integration of SVM+TLBO enhance the accuracy and efficiency of student performance prediction and learning ability evaluation?

Predicting student performance and evaluating learning ability are crucial tasks in educational contexts due to their significant impact on student success and instructional practices. By accurately forecasting student outcomes, educators can identify at-risk students early, provide targeted support, and improve overall academic achievement. Understanding students' learning abilities allows for the customization of teaching strategies, the development of personalized learning plans, and the optimization of educational resources to meet diverse student needs. Therefore, effective prediction of student performance and evaluation of learning ability are essential components of data-informed decision-making in education (Chen, 2023; Mohd Talib et al., 2023).

Previous research has highlighted the importance of student performance prediction, learning ability assessment, and the application of machine learning algorithms in educational data analysis. Studies have explored factors influencing student performance prediction, such as academic background, socio-economic status, and learning preferences. Additionally, research in educational psychology has examined various methods for evaluating learning ability, including standardized tests, observation, and self-assessment tools. The integration of machine learning algorithms, such as SVM, neural networks, and decision trees, has shown promise in enhancing predictive accuracy and informing instructional practices in educational environments (Alsubaie, 2023; Kumar et al., 2024).

The selection of the SVM+TLBO approach for this study is justified by its potential to address limitations of existing methods and contribute to advancing knowledge in the field of educational data analysis. SVM is known for its effectiveness in handling complex datasets, performing well in classification tasks, and providing robust predictions. By combining SVM with TLBO, an optimization technique inspired by the teaching-learning process, the study aims to enhance the predictive capability and efficiency of student performance prediction and learning ability evaluation. The synergistic integration of SVM+TLBO offers a novel approach to data mining in education, with the potential to improve the accuracy and reliability of predictive models in educational settings.