Improvement And Application Of Apriori Algorithm

Recent ten years, the ability of producing and collecting data by using information technology is improved dramatically. The size of data expands exceedly. So people hope that there be new techniques and tools to analyze these data intelligently and automatically, to find useful knowledge to support the decision-making. Therefore, facing the challenge of "the drowning in data but starving for knowledge", data mining emerges and develops flourishingly.Data mining is one of the most active research fields, especially in the fields of artificial intelligence and database research. Data mining is a kind of process that reveals potential useful knowledge from massive data. The association rule mining is a main research aspect of data mining. And the discovery of the frequent item sets is a key problem of the association rule mining.In this paper, the algorithm of the discovery of the frequent item sets and the application of association rules mining are studied. Main work can be concluded as follows:1. The step of associatin rule mining in data mining is studied. An overall analysis of the classical Apriori algorithm and Apriori_Tid algorithm is made, the key step of association rule mining and the deficiency of frequency item sets algorithm is pointed out.2. To the deficiency of Apriori algorithm, ZS_Apriori, a high-efficient algorithm for mining association rule, is put forward. This algorithm scans transaction database for only one time while it calculates supportor count, therefore, it reduces the scanning times; It compares the item counts of L_k-1 with K before calculates C_k, if the item counts of L_k-1 is lower than K, then C_k is equal to null. A lot of time is saved especially when K is larger. On the basis of the character of frequent item sets, the algorithm reduces the amount of candidate item sets.3. Association rule mining is applied to teaching quality evaluation in high university. The connection between class teaching effect and teachers' states is found, which provides decision-making information for educational departmen, and praises educational quality.4. Through the application of association rule mining to employment analysis in high university, we attempts to discover the associative relations between the educational attrivutes and the employment attributes of graduates and find the type of application person which the society needs, which provide guidance and data sustain for decision-maker to improve educational mode.