Actionable Objective Optimization for Suspicious Behavior Detection on Large Bipartite Graphs

We have been spotting massive suspicious behaviors on bipartite graph-based applications such as social networks and e-commercial platforms. Existing detection methods estimate the suspiciousness score of source users (e.g., followers, buyers) assuming that the behavioral patterns of suspicious source users (e.g., botnet followers, bully buyers) lead to abnormal high density in the graphs. A serious issue when putting the methods into real use is the false positives - the platforms cannot automatically suspend the source users just based on their suspiciousness scores. In this work, we revisit the problem of suspicious behavior detection from the perspective of the target users (e.g., followees, sellers), and provide them an effective and actionable solution using big behavior data analytics. We propose a novel method called Actionable Objective Optimization in which the variables are the target users' decisions rather than source users' scores. Experimental results show that our proposed actionable method consistently outperforms the state-of-the-art methods.