Data-Driven Precision Education: Combining Decision Tree and Cluster Analysis for Personalized Teaching.
Saved in:
| Title: | Data-Driven Precision Education: Combining Decision Tree and Cluster Analysis for Personalized Teaching. |
|---|---|
| Authors: | Yang, Dingyi1 (AUTHOR) jie1980yan@163.com, Yan, Jie2 (AUTHOR) yanjie1035@outlook.com, Chen, Qixin3 (AUTHOR) qi1983xin@163.com, Sun, Jingyi4 (AUTHOR) cjgzsunjy@163.com |
| Source: | Journal of Circuits, Systems & Computers. 7/30/2026, Vol. 35 Issue 12, p1-25. 25p. |
| Subjects: | CART algorithms, Cluster analysis (Statistics), Vocational education, Individualized instruction, Instructional systems design, Decision trees, K-means clustering |
| Abstract: | This paper aims to combine the decision tree (DT) algorithm and cluster analysis to achieve a multi-dimensional division of student characteristics in vocational education and address the limitation of traditional teaching models, which cannot accurately identify students' personalized needs. Through data-driven innovation in teaching strategies, it can improve educational effectiveness and provide practical guidance, and achieve the design and implementation of hierarchical and precise teaching plans for students. The paper used the K-means + + algorithm to cluster the characteristics of 1,200 students into three clusters: high, medium and low phenotypes. The paper used the CART (Classification and Regression Trees) algorithm to further refine the classification of each cluster of students and capture the characteristic differences of each group of students. Based on the clustering and detailed classification results, a teaching strategy combining hierarchical and personalized teaching was designed, and a 12-month intervention experiment was conducted to compare the traditional teaching strategy. After K-means + + clustering, the intra-cluster score variances of high phenotype, medium phenotype and low phenotype were 10.9, 13.8 and 17.1, respectively, and the accuracy of the CART detailed classification reached 97.4%. The innovative strategy in this paper showed significant advantages in terms of students' academic performance. In the 12th month, the scores of students using this strategy and the traditional strategy were 88 and 81 points, respectively. This strategy demonstrated the effectiveness and practicality of data-driven precision education by deeply exploring students' individual characteristics and designing targeted teaching paths. By combining clustering and detailed classification, the teaching method can accurately identify students' needs and significantly improve teaching outcomes. [ABSTRACT FROM AUTHOR] |
| Copyright of Journal of Circuits, Systems & Computers is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
Be the first to leave a comment!
