Towards better understanding of frequent itemset relationships through tree-like data structures
作者：
Highlights：
• We propose representation of frequent itemsets relationships as tree-like structures.
• We developed two algorithms for creating tree-like structures: top-down and bottom-up.
• Specific measures were defined to estimate the informative value of a structure.
• We developed a visualization tool with a high-level GUI in Python.
• Evaluation was performed successfully on a retail and a well-known benchmark classification dataset.
摘要
•We propose representation of frequent itemsets relationships as tree-like structures.•We developed two algorithms for creating tree-like structures: top-down and bottom-up.•Specific measures were defined to estimate the informative value of a structure.•We developed a visualization tool with a high-level GUI in Python.•Evaluation was performed successfully on a retail and a well-known benchmark classification dataset.
论文关键词：Transactional data,Association rules,Frequent itemset,Visualization,Tree-like structures,Market basket analysis
论文评审过程：Available online 30 September 2014.
论文官网地址：https://doi.org/10.1016/j.eswa.2014.09.040
