Parallel Mining of High Utility Itemsets From Large Transactional Databases

Provided by: IRD India
Topic: Data Management
Format: PDF
In this paper, the authors generate the high utility (profitable) item sets in a parallel environment, by considering the both profit and quantity of each item. The parallel mining of high utility item sets will take very less time than mining with the single system over large number of transactions. A Utility-Pattern tree (UP-tree) data structure (memory-resident) is used to store the information about the transactions. By UP-growth algorithm the candidate item sets are generated by scanning the database only twice.

Find By Topic