Research on degree of video completion of Internet videos with clustering algorithms

Clustering algorithms are some of the most important algorithms used to describe data attributes and very effective ways to mine and analyze big data set. In this paper, the whole description of vector space of Internet users is acquired by clustering and analyzing user behavior data set. Moreover, all users are divided into different clusters according to KPI which is to correlate different users in terms of their degree of video completion. Our research shows that KPI of total length correlates degree of completion better than other KPIs. This KPI is drastically negatively correlated with user degree of video completion. Finally, we compare the accuracy and efficiency of three different algorithms which we used to cluster our research data in this paper.