© 2015, IJARCSMS All Rights Reserved 224 | P a g e ISSN: 232 7782 (Online) 1 Computer Science and Management Studies  International Journal of Advance Research in Volume 3, Issue 11, November 2015 Research Article / Survey Paper / Case Study Available online at: www.ijarcsms.com Machine Learning Algorithms for Classification of Web Users in E-Commerce Portals B. Uma Maheswari 1 Research Scholar in Bharathiyar University, Coimbatore ,Tamil Nadu, India Dr. P. Sumathi 2 Asst. Professor, Govt. Arts College, Coimbatore, Tamil Nadu, India Abstract: The traffic on World Wide Web is increasing rapidly and huge amount of data is generated due to users’ numerous interactions with web sites. Web usage mining attempts to discover useful knowledge from the secondary data obtained from the interactions of the users with the Web. Data mining is one the analytical tools for analyzing information. It allow user to analyze data from many different range, classify it, and summarize the relationships. A user profile is erratic; a method is needed to update the evolving user profiles. Information regarding interested web users provides valuable information for web designer to quickly respond to their individual needs. Classification Algorithms can be used for classifying the interested users. This research compares the SVM and Evolving Agent behavior Classification based on Distributions algorithm in web usage mining. The experimental result shows the significant performance of the proposed algorithm. Classification algorithm can improve the accuracy of recommendation and also know the user behavior for improvement of design of a website. Keywords: Web usage mining, Evolving Agent behavior Classification based on Distributions algorithm, Support vector machine, User behaviour I. INTRODUCTION WUM deals with understanding user behavior in interacting with the web or with a website. One of the aims is to obtain information that may assist web site reorganization or assist site adaptation to better suit the user. Web usage mining model is a kind of mining to server logs and its aim is getting useful users’ access information in logs to make sites can perfect themselves with appropriate users’ requirements, serve users better and get more economy benefit. Web mining is the application of data mining techniques to extract knowledge from web data including web documents, hyperlinks between documents, usage logs of websites, etc. Web Usage Mining is a part of Web Mining which in turn, is a part of Data Mining. As data mining is the process of extracting meaningful and valuable information from large volume of data. Web usage mining is the process of mining useful information from server logs. Web usage mining is the process of finding out what users are looking for on internet. This information can then be used in a variety of ways such as, improvement of websites, e-commerce, website personalization, user future request prediction etc. The use of this type of web mining helps to gather the important information from customers visiting the site. This work focused on the web usage mining and identification of user’s behavior on the web. The behavior of users on the web can be analyzed by extracting useful information from web log data. Web log file is automatically created and manipulated by every hit to the website. Log files usually contain noisy and irrelevant data. Preprocessing is done to remove unnecessary data from log file. After then pattern discovery and pattern analysis can be performed for extracting useful patterns. Such interested patterns can be generated using several techniques like classification, clustering, association rule mining. In this paper we deal with classification algorithms for studying the user/client behavior and for the generation of interested user patterns. Consideration of interested web users can be done on the basis of probability of relevant and irrelevant links. Relevant links are the most visited links that can be identified on the basis of time spend on a webpage or number of hits done to a particular link.