As the size of the real-time click steam data increases, it is difficult to find and extract the essential user navigation behavioral pattern on e-commerce applications. Due to the huge growth of the e-commerce applications, the complications of web applications and web navigation can be further applied to various things, such as the identification of the user's frequent patterns, predicting future user requests, etc... Most of the existing methods try to find the hidden patterns from the web server log files or click stream data. These log files are used to analyze the user navigation patterns and its historical information. Also, these models are not applicable to dynamic extraction of user behavior patterns in real time web applications such as e-learning or e-commerce. In this paper, a novel user navigation behavior prediction model is proposed using the mathematical framework on the large click stream data. Experimental results proved that the present method is better than the traditional methods in terms of performance metrics are concerned.
Volume 11 | Issue 5