An Efficient Data Mining Algorithm based on the Database Characteristics

데이터 베이스 특성에 따른 효율적인 데이터 마이닝 알고리즘

  • 박지현 ((주)더모스트 시스템사업부) ;
  • 고찬 (서울산업대학교 컴퓨터공학과)
  • Published : 2006.08.25


Recently with developments of an internet and web techniques, the amount of data that are stored in database is increasing rapidly. So the range of adaption in database has been expanded and a research of Data Mining techniques finding useful skills from the huge database has been progressed. Many original algorithms have been developed by cutting down the item set and the size of database isn't required in the entire course of creating frequent item sets. Although those skills could save time in some course, it requires too much time for adapting those techniques in other courses. In this paper, an algorithm is proposed. In an Transaction Database that the length of it's transactions are short or the number of items are relatively small, this algorithm scans a database once by using a Hashing Technique and at the same time, stores all parts of the set, can be appeared at each transaction, in an Hash-table. So without an influence of n minimum percentage of support, it can discover a set of frequent items in more shorter time than the time what is used by an original algorithm.