A Study on Mining Top Utility Itemsets In A Single Phase

This paper presents a study on finding Top K itemsets with high utility. High Utility Item sets (HUI) mining has emerged as an interesting and challenging research topic in data mining. It finds applications in web-click analysis, cross-marketing in retail stores and bio medical analysis etc. The number of high-utility itemsets that can be extracted from a transactional database depends upon the value of minimum utility threshold. It is often difficult for a user to find a suitable threshold value which fits their purpose. The database can generate many high-utility itemsets at low threshold value and very few itemsets at higher threshold values. In order to relieve the user from this tedious task, we use an efficient algorithm named TKO for mining top-k high utility itemsets from a large transactional database. The parameter k can be set by the user according to his/her needs. We conduct extensive experiments on real and synthetic datasets and the experimental results demonstrate the effectiveness of our Threshold raising strategies in terms of total execution time and the memory usage.