This paper primarily focuses on discovering the frequent sequential patterns without sorting the subsequences present in the sequence of the dataset. The proposed algorithm utilizes numerically converted values of subsequence item to identify the exact order of the patterns efficiently. Most of the existing algorithms for brevity consider only the sorted data or initially sorts the unsorted data to find the patterns. But there are certain circumstances where the data has to be presented and mined without ordering the data. This paper proposes a new algorithm named “DATA as it IS Algorithm” to find frequent sequential patterns and prune away the infrequent items at the beginning stages of the process. The experimental evaluation portrayed that the proposed DAIS algorithm performs effectively and effectively and outscores the existing algorithms by an order of magnitude.
Keywords: Sequential patterns, frequent patterns, without ordering
