Improved clustering and association rules mining for university student course scores
Tian Zhang, Changchuan Yin, Lin Pan · 2017
In order to help students improve their performance in college, this paper discovered the association rules among the scores of different courses, and introduced the parameter "Interest" to help filtering the rules. In order to meet the demand for score discretization in association rules mining, this paper analyzed score distribution characteristics, and proposed an initial cluster center optimized and isolated point pre-processed K-means clustering algorithm based on sample distribution density. This algorithm can reduce the sensitivity of K-means algorithm to initial cluster centers and isolated points. The numerical results and evaluation index show that this algorithm can meet the requirements of score discretization. The result of association rules mining using this improved K-means algorithm for score discretization can efficiently reduce the invalid and wrong rules.