Mining High Utility Itemsets Based On Multiple Minimum Support And Multiple Minimum Utility Thresholds

High utility itemset mining refers to mine itemsets having utility value greater than user specified threshold from a transactional database.It is an important data mining task and has a wide range of real life applications.Mining high utility itemset is a challenging task and several approaches has been proposed in the recent years.The proposed approaches use different search strategy,data structure,pruning technique to make the approaches efficient.Algorithms like HUIM-MMU and MHU-Growth overcome the limitation of using a single threshold for the whole database.However they still struggle with 'rare item problem'.The most efficient high utility itemset mining algorithm EFIM introduces two upper bounds named sub-tree utility and local utility.By combining ideas from the HUIM-MMU,MHU-Growth and EFIM,I introduce two algorithm named HUIM-MMSU and HUIM-IMMSU.HUIM-MMSU is a candidate generation and retest based algorithm,which relies on sorted downward closure(SDC)property.On the other hand,HUIM-IMMSU uses a tree-like data structure.Experiment result shows that the proposed two algorithms can effectively discover high utility itemsets in a transactional database.