The Applied Research Of Decision-tree And Association Rules Analysis On The Vocational College Enrollment

In recent years, government supported vocational college and vocational college expanded increasingly which all contributed to the fierce competition among colleges. Faced with competition, the vocational colleges in order to take a place, colleges must improve registration rate and acquire quality resources. At present, some vocational colleges have established its own recruiting system with the aim to make the enrollment work more efficient via internet information platform. But recruiting system only performs limited functions, such as information registration and storage. Recruiting system cannot help us to resolve the real problem. As a result, the emergence of data mining technology, it can be make full use of statistics for recruitment work with aim to discover useful value. We hope the system can provide scientific guidance for recruitment work and policy.This thesis analyzes the factors that influence registration rate by using the decision tree classification algorithm and association rule to further investigate student enrollment information. The thesis was discussed mainly from the following aspects:1?The research mainly explores the basic knowledge of data mining and the decision tree classification algorithm and association rule in data mining technology. The thesis also makes a comparison about different arithmetic, including 1D3, C4.5 arithmetic of decision tree classification algorithm and Apriori of association rule.2?Based on practical work, the thesis disposes the data according to vocational college demand of data archiving by which ensures an efficient data mining work.3?The thesis employs C4.5 of decision tree classification algorithm and Apriori algorithm of association rule with aim to compare and analyze data, at the same time, enrollment dataset using the data mining algorithm on the platform of weka, which help us to get relevant conclusions. As a result, we can explore the similarities and differences of the same data by searching different data mining methods through which we can acquire accurate data to support our recruitment decision.