An Ensemble Click Model for Web Document Ranking

Annually, web search engine providers spend more and more money on documents ranking in search engines result pages (SERP). Click models provide advantageous information for ranking documents in SERPs through modeling interactions among users and search engines. Here, three modules are employed to create a hybrid click model; the first module is a PGM-based click model, the second module in a deep neural network click model and finally the last one in a similarity measure based on SimRank. Hybrid click model tries to predict users' clicks behavior on the documets which are represented in SERPs. Indeed, an MLP classifier has been employed to provide the final decision based on modules which are used in Hybrid click model. The proposed system is evaluated on the Yandex dataset as a standard click log data set. The results demonstrate the superiority of our model over the state-of-the-art click models in terms of perplexity.