Mining Positive and Negative Sequential Patterns with Multiple Minimum Supports in Large Transaction Databases

Sequential patterns mining is an important research topic in data mining and knowledge discovery. The objective of mining sequential patterns is to find out frequent sequences based on the user-specified minimum support threshold, which implicitly assumes that all items in the data have similar frequencies. This is often not the case in real-life applications. If the frequencies of items vary a great deal, we will encounter the dilemma called the rare item problem. In this paper, an efficient algorithm to discover sequential patterns with multiple minimum supports is proposed. The algorithm can not only discover sequential patterns forming between frequent sequences, but also discover sequential patterns forming between either frequent and sequences rare sequences or among rare sequences. Moreover, an algorithm for mining positive and negative sequential patterns with multiple minimum supports is designed simultaneously.