Analysis of Frequent URLs for a Recommender System Using Performance Based Transposition Algorithm

The explosive and rapid growth of internet technologies in recent decades has imposed a heavy information burden on web users. Therefore, the popularity of recommender systems has evolved to provide suggestions and recommendations to the user for relevant information from web according to their preferences. Recommendation of items is based on two types of ratings, i.e., implicit ratings and explicit ratings. In implicit ratings, frequent and useful URLs of web pages are generated using various data mining techniques such as classification, clustering and frequent pattern mining and Association Rule Mining (ARM). The ARM technique is used to discover the frequent item sets and rules from transaction database and it is also used to extract hidden knowledge from datasets that can be used by organization’s decision makers to improve overall profit. The proposed approach will generate frequent URLs using an ARM technique called Performance Based Transposition Algorithm (PBTA). The strong association rules, maximal item sets, and closed item sets will also be generated along with frequent item sets (URLs) through extensive experiments.