Mining Transactional Databases for Frequent and High-Utility Fuzzy Sequential Patterns With Time Intervals

The field of data mining is progressing rapidly presenting researchers with many opportunities for research. Sequential pattern mining is a popular and long established technique in data mining which extracts data in the form of sequential patterns, satisfying a threshold value, such as utility, support, profit or a combination of these. The application of fuzzy theory in sequential pattern mining has also been favored leading to more natural linguistic representation. Researchers have proposed various hybrid algorithms with fuzzification of any one parameter, such as time or quantity. This paper proposes a hybrid fuzzy algorithm for mining of frequent and high utility sequential patterns with fuzzification of both purchase time and purchase quantity parameters, thereby giving more useful fuzzy sequential patterns. Experimental results also prove that the proposed algorithm is better than the existing algorithms.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.