Compact transaction database for efficient frequent pattern mining

Mining frequent patterns is one of the fundamental and essential operations in many data mining applications, such as discovering association rules. In this paper, we propose an innovative approach to generating compact transaction databases for efficient frequent pattern mining. It uses a compact tree structure, called CT-tree, to compress the original transactional data. This allows the CT-a priori algorithm, which is revised from the classical a priori algorithm, to generate frequent patterns quickly by skipping the initial database scan and reducing a great amount of I/O time per database scan. Empirical evaluations show that our approach is effective, efficient and promising, while the storage space requirement as well as the mining time can be decreased dramatically on both synthetic and real-world databases.