Data Analysis of Educational Evaluation Using K-Means Clustering Method.

Area of Science:

• Data Science
• Educational Technology
• Machine Learning

Background:

• Educational data is rapidly expanding, creating challenges in information extraction and analysis.
• Effective data analysis is crucial for informed decision-making in education.

Purpose of the Study:

• To develop a data analysis model for education evaluation using K-means clustering.
• To improve the accuracy and efficiency of analyzing students' comprehensive quality data.

Main Methods:

• Utilized K-means clustering for educational data analysis.
• Applied Analytic Hierarchy Process (AHP) to determine index weights for student quality.
• Implemented improved sampling and sample partition clustering for large datasets.

Main Results:

• Achieved a best accuracy of 95.6% in experimental data analysis.
• Demonstrated superior performance compared to Mi cluster (12.1% higher) and DRCluster (6.8% higher) algorithms.
• Successfully identified important features for analysis system mining.

Conclusions:

• The K-means clustering model provides an effective framework for educational data mining.
• The approach aids in diagnosing learning problems and developing student management strategies.
• This method offers significant improvements in accuracy for educational data evaluation.