A Markov chain model for integrating behavioral targeting into contextual advertising

Both Contextual Advertising (CA) and Behavioral Targeting (BT) are playing important roles in online advertising market. Recently, the problem of how to integrate BT strategies into CA has attracted much attention from both industry and academia. However, to our best knowledge, few research works have been published to provide BT solutions in CA. In this paper, we propose a new notion of relevance between webpages and ads based on users' online click-through behaviors from BT's perspective. Compared with the classical behavior targeting method where only users' history interests are considered, we pay more attention to the click probability of ads from a webpage where the relevance between them is evaluated. Moreover, a combination model integrating behavioral relevance and contextual relevance for matching ads and webpags is presented. The model parameters are learnt from a dataset consisting of 200 webpages and 35,880 ads. Experimental results show that our integrated strategy indeed outperforms the strategies that only consider either behavioral relevance or contextual relevance. The best model achieves a 18.1% improvement in precision over single strategies.