Markov decision processes for ad network optimization

摘要

In this paper we examine a central problem in a particular advertisingudscheme: we are concerned with matching marketing campaigns that produceudadvertisements (“ads”), to impressions — where “impression” is a general termudfor any space in the internet that can display an ad. In this paper we propose audnew take on the problem by resorting to planning techniques based on MarkovudDecision Processes, and by resorting to plan generation techniques that haveudbeen developed in the AI literature. We present a detailed formulation of theudMarkov Decision Process approach and results of simulated experiments