Collaborative networks are composed of experts who cooperate with each other to complete specific tasks, such as resolving problems reported by customers. A task is posted and subsequently routed in the network from an expert to another until being resolved. When an expert cannot solve a task, his routing decision (i.e., where to transfer a task) is critical since it can significantly affect the completion time of a task. In this work, we attempt to deduce the cognitive process of task routing, and model the decision making of experts as a generative process where a routing decision is made based on mixed routing patterns.

In particular, we observe an interesting phenomenon that an expert tends to transfer a task to someone whose knowledge is neither too similar to nor too different from his own. Based on this observation, an expertise difference based routing pattern is developed. We formalize multiple routing patterns by taking into account both rational and random analysis of tasks, and present a generative model to combine them. For a held-out set of tasks, our model not only explains their real routing sequences very well, but also accurately predicts their completion time. Under three different quality measures, our method significantly outperforms all the alternatives with more than 75% accuracy gain. In practice, with the help of our model, hypotheses on how to improve a collaborative network can be tested quickly and reliably, thereby significantly easing performance improvement of collaborative networks.