The Research And Application Of The Incremental Updating Optimized Association Rules Mining Algorithms

The association rules mining, as an important part in data mining, has applied successfully in the fields of commerce, education, CRM research etc., which has become a most important and most active branch in data mining. Since the concept of association rules and Aprior which is the first association rules mining algorithm are proposed by Agrawal, ,lots of researchers have broadly researches on Apriori algorithm because its commercial and theoretic values. On this basis,many new association rules mining algorithms were proposed by optimizing and improving Apriori algorithm continuously in order to improve the efficiency of data mining. Whereas the efficiency of these algorithms is enhanced, there are also some deficiencies. In addition, there are two prevalent problems in mining association rules: How to acquire results efficiently and immediately when database updates constantly? Usually, it's necessary to set some parameters for customers before mining, and mostly they have to adjust these parameters time after time to acquire the satisfactory rules, thus how to calculate efficiently during the repetitious process? Here, incremental updating algorithms can solve these problems.Based on the previous researches, we explore the incremental updating algorithms on mining association rules in this paper, the main content of which can be summed up as follows:(1) Introduce the concepts and applications of data mining and association rules, and make a research on the classic Apriori algorithm, point out the advantage and the defects of this algorithm.(2) Researches on mining technology of association rules in continuous data updating, analyses the basic theory of FUP algorithm and expatiate it specifically, point out its advantages and disadvantages. Because of most incremental updating algorithms scans the database for many times, and cannot differentiate the essentiality of different data by interval, this paper introduces a new time significance based on incremental updating association rules mining algorithm--Apriori+.(3) Simply states the uses of Apriori+ algorithm in cross-selling of retail trade, and proves its validity by tests.