How to Battle Click Spam on the Ground?

Most of today’s internet services utilize user feedback (clicks) to improve the quality of their services. For example, search engines use click information as a key factor in document ranking. As a result, some websites cheat to get a higher rank by fraudulently increasing clicks to their pages. This phenomenon known as click spam is automatically initiated by programs called click bot . In this paper, we propose a novel classification-based technique to identify fraudulent user clicks in a fast and practical manner. We first analyze user session behaviors to extract the important features of normal and abnormal sessions, and then implement our method in real environments. Experimental results show that our approach can detect fraudulent clicks with a precision of up to 94% which outperform the previous work by 2%.

Keywords:

click spam , botnet detection , anomaly detection