Fuzzy logic based methods together with the techniques from Artificial Intelligence have gained importance. It provides a sound foundation to handle imprecision and vagueness as well as mature inference mechanisms using varying degrees of truth. Sequential pattern mining is the mining of frequently occurring ordered events or to discover frequent subsequences as patterns in a sequence Database. Frequent sequential pattern discovery can essentially be thought of as association rule discovery over a temporal database. The time interval sequential patterns provide more valuable information than a conventional sequential pattern. However, this approach may cause a sharp boundary problem. In this paper, we aim to introduce a new algorithm "FTI-Apriori-Event" which predicts an optimum fuzzy time interval for the future occurrence of a given event based on fuzzy set as they provide a smooth transition between member and nonmember of a set, which in turn helps in "providing right products at the right time to the right customers".
展开▼
