Practice of Web Data Mining Methods Application

Abstract

Practice of Web Data Mining Methods ApplicationRecent growth of information on the Internet imposes high demands on the effectiveness of processing algorithms. This paper discusses some algorithms from the field of Web Data Mining which have proved effective in many existing applications. The paper is divided into two logical parts; the first part provides a theoretical description of the algorithms, but the second one contains examples of their successful use to solve real problems. Search algorithms of vague duplicates of documents are currently actively used by all the leading search engines in the world. The paper describes the following algorithms: shingles, signature methods and image-based algorithms. Such methods of classification as a method of fuzzy clustering to-medium (Fuzzy cmeans/ FCM clustering) and clustering by ant colony (Standard Ant Clustering Algorithm SACA) are considered. In conclusion, the experience of the successful application of fuzzy clustering in conjunction with the software toolkit DataEngine to improve the efficiency of the bank "BCI Bank" is described as well as the sharing of the ant colony clustering method in conjunction with linear genetic programming to meet the increasing efficiency of predicting the load on the servers of high load Internet portal Monash Institut.