• Mohamed Jamshad K

High utility pattern mining is the discovery of groups of patterns that not only co-occur but also carry a high return. For candidate creation in two-phase pattern mining, an Apriori method is employed. However, candidate generation is expensive, and if the number of candidates is large, scalability and efficiency become bottleneck issues. Many attempts have been made to reduce the number of candidates produced in the first phase, but the problem remains when the raw data includes a large number of transactions or the minimal utility criterion is too low. The MHU-ISM technique for High Utility Mining was suggested in this article. This takes into account not just the frequency of the itemsets but also the usefulness connected with the itemsets. The word utility relates to the significance or usefulness of the appearance of the itemset in transactions, as measured in measures such as profit, sales, or any other user preferences. The goal of High Utility Itemset Mining is to find itemsets with utility values greater than a certain threshold. Some high utility itemset mining methods, such as second-Phase and FP-Growth, have been suggested in current systems. This approach is a memory-efficient way for mining high-utility item sets from transactional databases. This method uses less memory space and takes less time to execute than current techniques.

HUI, FP-Growth, Utility pattern mining, HTM, MHU-ISM

"MHU-ISM: MINING HIGH UTILITY ITEM SETS MINING IN TRANSACTIONAL DATABASES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.2, Issue 11, page no.1230-1237, November-2015, Available :http://www.jetir.org/papers/JETIR1701590.pdf

"MHU-ISM: MINING HIGH UTILITY ITEM SETS MINING IN TRANSACTIONAL DATABASES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.2, Issue 11, page no. pp1230-1237, November-2015, Available at : http://www.jetir.org/papers/JETIR1701590.pdf