WLPMiner: weighted frequent pattern mining with length-decreasing support constraints

• Authors: Unil Yun;John J. Leggett
• Venue: PAKDD'05 Proceedings of the 9th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
• Year: 2005

Two main concerns exist for frequent pattern mining in the real world. First, each item has different importance so researchers have proposed weighted frequent pattern mining algorithms that reflect the importance of items. Second, patterns having only smaller items tend to be interesting if they have high support, while long patterns can still be interesting although their supports are relatively small. Weight and length decreasing support constraints are key factors, but no mining algorithms consider both the constraints. In this paper, we re-examine two basic but interesting constraints, a weight constraint and a length decreasing support constraint and propose weighted frequent pattern mining with length decreasing constraints. Our main approach is to push weight constraints and length decreasing support constraints into the pattern growth algorithm. For pruning techniques, we propose the notion of Weighted Smallest Valid Extension (WSVE) with applying length decreasing support constraints in weight-based mining. The WSVE property is applied to transaction and node pruning. WLPMiner generates more concise and important weighted frequent patterns with a length decreasing support constraint in large databases by applying the weighted smallest valid extension.