1. Web Analytics Software to Predict the Behavior of Website Visitors Constantine J. Aivalis Technological Education Institute of Crete University of Peloponnese costis.aivalis@gmail.com
2. Content Introduction The Problem The Solution Architecture Functionality DBMS Results Customer Behavioral Model Graph Measurements Future Work Applications Conclusion 25/9/2011 2 Web Analytics Software to Predict the Behavior of Website Visitors
3. Introduction WWW is today's common business platform. E-Commerce infrastructure must be reliable, robust and scalable. Web systems produce huge amounts of user activity data that are often unused. User activity data must be converted to information. Intelligent Customer classification allows better customized services. 25/9/2011 3 Web Analytics Software to Predict the Behavior of Website Visitors
4. The Problem E-shops often operate in “blind folded” fashion. Only successful sales transactions are visible to the administration and management. Most e-Commerce systems have no built-in performance measuring mechanisms. Only registered-customer actions are taken into consideration. Visitor majority may not be customers yet. Their behavior has to be analyzed in order to make them. Access log files include all interaction data details. Manual access log file scrutinizing is too inconvenient to be performed on regular basis. 25/9/2011 4 Web Analytics Software to Predict the Behavior of Website Visitors
5. The Solution Parsing and “cleaning” log files. Extraction and transfer into a DBMS. Information Generation. Cross correlation of log file and e-Commerce site data for seamless integration. Anonymous and registered visitor hits can be analyzed through their IP-addresses. Crawlers and Web-Bots can be recognized via IP-address and their behavioral patterns. Implementation of a software tool that directly measures the operational performance of the e-shop in nearly real time. 25/9/2011 5 Web Analytics Software to Predict the Behavior of Website Visitors
8. DBMS 25/9/2011 8 Web Analytics Software to Predict the Behavior of Website Visitors
9. Results Visitor Behavioral Analysis (including non registered visitors) Dynamical generation of various statistics Graph generation Tendency Forecasts Data Mining Possibilities Exception Reports Measurements and e-shop performance comparison Time Period performance analysis 25/9/2011 9 Web Analytics Software to Predict the Behavior of Website Visitors
10. Customer Behavioral Model Graph 10 25/9/2011 Web Analytics Software to Predict the Behavior of Website Visitors
12. Measurements Order Values/Numbers Visits Time spent per product or service Accesses per product or service Orders per Product or service Bots visited Visitors Uncompleted ordering sessions Profitable customer groups Profitable products or services Overall profits Promotion impact 25/9/2011 Web Analytics Software to Predict the Behavior of Website Visitors 12
13. Future Research Analysis of bots and their search engine behavior concerning e-shops. Recognition of anonymous bots and spiders through their access patterns. Customer rating and evaluation application based on non purchase behavior. Agent implementation in order to automatically promote the rank of less sought for products. Methodology for RIAs 25/9/2011 Web Analytics Software to Predict the Behavior of Website Visitors 13
14. Thank You Constantine Aivalis costis.aivalis@gmail.com 25/9/2011 Web Analytics Software to Predict the Behavior of Website Visitors 14