Data Mining Algorithms for the Construction of Curriculum Evaluation System and Teaching Quality Improvement Based on the Concept of Professional Accreditation

Abstract

This study presents a novel approach towards constructing a Curriculum Evaluation System (CES) aimed at enhancing teaching quality through the integration of data mining algorithms and professional accreditation standards. The CES framework leverages data analytics to analyze diverse sources of educational data, including student performance metrics and teacher evaluations, to inform evidence-based decision-making processes. Through a pilot study conducted in a secondary school setting, the effectiveness of the CES in improving student academic performance and teaching effectiveness was evaluated. Results indicate a statistically significant improvement in student grades, pass rates, and standardized test scores following the implementation of the CES framework. Moreover, an increase in teacher evaluation scores and the percentage of satisfied teachers reflects a positive perception of teaching quality and curriculum effectiveness among educators. The alignment of the CES with professional accreditation standards ensures compliance with industry benchmarks and fosters a culture of continuous improvement within educational institutions. Despite challenges associated with data availability and interpretation, the CES framework offers a promising avenue for advancing teaching quality and curriculum development through data-driven methodologies. This study contributes to the growing body of research on educational assessment practices and underscores the importance of leveraging data mining algorithms for educational innovation and excellence.