Abstrato

TP-Mine: An Approach to Determine the Transitional Patterns and their Significant Milestones

Radhika Katkum, Harish Kalla, Arun Roy Vadde, Rama Krishna T

A transaction database usually consists of a set of time-stamped transactions. Mining frequent patterns in transaction databases has been studied extensively in data mining research. However, most of existing frequent pattern mining algorithms does not consider the time stamps associated with transactions. We extended the existing frequent pattern mining framework to take into account the time stamp of each transaction and discover patterns whose frequency dramatically changes over time. We define a new type of patterns, called Transitional Patterns, to capture the dynamic behavior of frequent patterns in a transaction database. Transitional patterns include both positive and negative transitional patterns. Their frequencies increase or decrease dramatically at some time points of a transaction database. We introduced the concept of significant milestones for a transitional pattern, which are time points at which the frequency of the pattern changes most significantly. Moreover, we developed an algorithm to mine the set of transitional patterns along with their significant milestones from the transaction database