MSK: A Grade Mining Method for Second-Class Based on MeanShift and K-means

With the advent of the era of big data, more and more data are accumulated by the second class in colleges and universities, and how to effectively analyze and use them has become the research focus. A novel clustering algorithm named MeanShift-K-means (MSK) is proposed to assess the scores and get the relationship between scores and graduation. Firstly, the MeanShift vector is calculated by Gaussian kernel function, Then MeanShift algorithm is used to obtain the initial clustering center points in K-Means, instead of random selection. Secondly, the improved K-means algorithm was applied to assess the second class in a university. The results show that the MSK algorithm has better clustering effect than the traditional Kmeans algorithm and Canopy-K-means algorithm, which is more helpful to recommend activities for college students and to provide predictive guidance and decision-making basis for administrators.