Improving Real-Time Bidding Using a Constrained Markov Decision Process
| Autor: | Radu State, Omar Cherkaoui, Mats Brorsson, Georgios Varisteas, Redouane Sassioui, Manxing Du |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Computer science [C05] [Engineering
computing & technology] Operations research Computer science business.industry Display advertising TheoryofComputation_GENERAL Partially observable Markov decision process 02 engineering and technology Real-time bidding Bidding Markov model Sciences informatiques [C05] [Ingénierie informatique & technologie] 020204 information systems 0202 electrical engineering electronic engineering information engineering Common value auction 020201 artificial intelligence & image processing Markov decision process Bid price business |
| Zdroj: | Proceedings of the 13th International Conference on Advanced Data Mining and Applications (pp. 711-726). Springer (2017). Advanced Data Mining and Applications ISBN: 9783319691787 ADMA |
| Popis: | Online advertising is increasingly switching to real-time bidding on advertisement inventory, in which the ad slots are sold through real-time auctions upon users visiting websites or using mobile apps. To compete with unknown bidders in such a highly stochastic environment, each bidder is required to estimate the value of each impression and to set a competitive bid price. Previous bidding algorithms have done so without considering the constraint of budget limits, which we address in this paper. We model the bidding process as a Constrained Markov Decision Process based reinforcement learning framework. Our model uses the predicted click-through-rate as the state, bid price as the action, and ad clicks as the reward. We propose a bidding function, which outperforms the state-of-the-art bidding functions in terms of the number of clicks when the budget limit is low. We further simulate different bidding functions competing in the same environment and report the performances of the bidding strategies when required to adapt to a dynamic environment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|