Frequent Sequence Mining with Weight Constraints in Uncertain Databases

Abstract

Pattern mining has drawn attention of researchers because of its high applicability to mine patterns or sequences from probabilistic databases in various real-life applications. Weight of an item, a pattern, or a sequence help data scientists extract interesting information and knowledge for these applications. However, most related works do not handle sequences with weight constraints in uncertain databases. In this paper, we introduce the concept of weighted uncertain sequence mining. We also propose a new algorithm to mine sequences with weight constraints from uncertain databases. The algorithm is applicable for data science tasks like finding changes in fashion trends and forecasting weather or natural calamities. Our evaluation results show the effectiveness of the algorithm and its superiority over the related works.