This chapter focuses on predicting web user behaviors. When web users enter a website, every move they make on that website is stored as web log files. Unlike the focus group or questionnaire, the log files reflect real user behavior. It can easily be said that having actual user behavior is a gold value for the organizations. In this chapter, the ways of extracting user patterns (user behavior) from the log files are sought. In this context, the web usage mining process is explained. Some web usage mining techniques are mentioned.
TopIntroduction
Today, the Internet is an essential part of daily life. Thanks to the Internet, people easily connect, buy anything they want, share their thoughts. Selling services and goods through online positively affect businesses. At this point, the web sites which are well designed have a massive advantage to other ones. Most companies use their commercial web sites as a connector tool with their customers. They can easily see what customers need and then, can improve their selling and marketing strategies.
The Internet users leave their traces while are navigating on a web site. These traces are called user path, which is the essential user-generated data source. Discovering user path, businesses gain valuable information for their marketing strategies, detect potential risks, take the strategic decisions. Marketing managers aim to attract potential customers (visitors, users) to their websites, understand their purchasing behavior, and ensure the continuity of their customers. A potential customer has been attracted to the site and commences a visit, the next set of issues centers on what transpires while the visitor is there (Bucklin, 2008). Therefore, database marketing may help a firm to better market to their customers (McCarty & Hastak, 2007). The aim here is to analyze the customer's transaction and behavioral data to predict the future behavior of the customer, such as the purchase (Hughes, 2005). Database marketing is efficient because of the use of data-mining techniques based on machine learning that allows marketers to segment their customer databases better.
While users are browsing the pages on the Internet, purchasing products/services, sharing on social media, the tracks they leave are stored on the web servers. Data of customers’ browsing behaviors include among others customers’ IP address, operating system, keywords used for searching, URL of Web pages visited, time of page visit, and length of time spent on a Web page. The data, which is produced and stored on the web, can be analyzed by Web mining. Web mining is the process of valuable information discovery from Web data.
Web usage mining can be defined as the application of data mining techniques to discover usage patterns from Web data (Srivastava, Cooley, Deshpande, & Tan, 2000). Web usage mining refers to the discovery of user access patterns from Web usage logs, which record every click made by each user, and applies many data mining algorithms. One of the critical issues in Web usage mining is the pre-processing of clickstream data in usage logs to produce the correct data for mining. Web usage mining aims to study user clicks and their applications to e-commerce and business intelligence. The objective is to capture and model behavioral patterns and profiles of users who interact with a Web site. Such patterns can be used to understand the behaviors of different user segments better, to improve the organization and structure of the site, and to create personalized experiences for users by providing dynamic recommendations of products and services (Liu, 2007). The generated data which are called web log data is stored in the web servers. Web Usage Mining uncovers the hidden patterns underlying the Web Log Data. These patterns represent user browsing behaviors which can be employed in detecting deviations in user browsing behavior in web-based applications where data privacy and security is of utmost importance. Knowledge Discovery from Web Log Data has an essential role in serving the needs of web-based applications.
The aim of this chapter is seeking ways of determining user behavior. Predicting customers’ interests are based on the data gathered from many customers. The current behavior of visitors (customers) will be maintained in the future. The similarity between users is used to predict the levels of product preference. The Web usage mining process proposed by Srivastava et al. (2000) for web usage mining will be mentioned, and the techniques frequently used to predict user behavior (in the estimation of the next click of the user) will be explained.