Matches in SemOpenAlex for { <https://semopenalex.org/work/W3117488143> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3117488143 abstract "In e-commerce advertising, the ad platform usually relies on auction mechanisms to optimize different performance metrics, such as user experience, advertiser utility, and platform revenue. However, most of the state-of-the-art auction mechanisms only focus on optimizing a single performance metric, e.g., either social welfare or revenue, and are not suitable for e-commerce advertising with various, dynamic, difficult to estimate, and even conflicting performance metrics. In this paper, we propose a new mechanism called Deep GSP auction, which leverages deep learning to design new rank score functions within the celebrated GSP auction framework. These new rank score functions are implemented via deep neural network models under the constraints of monotone allocation and smooth transition. The requirement of monotone allocation ensures Deep GSP auction nice game theoretical properties, while the requirement of smooth transition guarantees the advertiser utilities would not fluctuate too much when the auction mechanism switches among candidate mechanisms to achieve different optimization objectives. We deployed the proposed mechanisms in a leading e-commerce ad platform and conducted comprehensive experimental evaluations with both offline simulations and online A/B tests. The results demonstrated the effectiveness of the Deep GSP auction compared to the state-of-the-art auction mechanisms." @default.
- W3117488143 created "2021-01-05" @default.
- W3117488143 creator A5007735734 @default.
- W3117488143 creator A5007939424 @default.
- W3117488143 creator A5009324842 @default.
- W3117488143 creator A5016620131 @default.
- W3117488143 creator A5050396482 @default.
- W3117488143 creator A5059190563 @default.
- W3117488143 creator A5059373349 @default.
- W3117488143 creator A5060575116 @default.
- W3117488143 creator A5062939922 @default.
- W3117488143 creator A5091646587 @default.
- W3117488143 date "2021-03-08" @default.
- W3117488143 modified "2023-09-23" @default.
- W3117488143 title "Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising" @default.
- W3117488143 cites W1557860566 @default.
- W3117488143 cites W1964975266 @default.
- W3117488143 cites W2070376024 @default.
- W3117488143 cites W2082943428 @default.
- W3117488143 cites W2085192478 @default.
- W3117488143 cites W2088640816 @default.
- W3117488143 cites W2130521818 @default.
- W3117488143 cites W2153500072 @default.
- W3117488143 cites W2508468814 @default.
- W3117488143 cites W2618087227 @default.
- W3117488143 cites W2972510393 @default.
- W3117488143 cites W2998596932 @default.
- W3117488143 cites W3003266170 @default.
- W3117488143 cites W3012829370 @default.
- W3117488143 cites W3123656117 @default.
- W3117488143 cites W3145413957 @default.
- W3117488143 doi "https://doi.org/10.1145/3437963.3441771" @default.
- W3117488143 hasPublicationYear "2021" @default.
- W3117488143 type Work @default.
- W3117488143 sameAs 3117488143 @default.
- W3117488143 citedByCount "11" @default.
- W3117488143 countsByYear W31174881432021 @default.
- W3117488143 countsByYear W31174881432022 @default.
- W3117488143 countsByYear W31174881432023 @default.
- W3117488143 crossrefType "proceedings-article" @default.
- W3117488143 hasAuthorship W3117488143A5007735734 @default.
- W3117488143 hasAuthorship W3117488143A5007939424 @default.
- W3117488143 hasAuthorship W3117488143A5009324842 @default.
- W3117488143 hasAuthorship W3117488143A5016620131 @default.
- W3117488143 hasAuthorship W3117488143A5050396482 @default.
- W3117488143 hasAuthorship W3117488143A5059190563 @default.
- W3117488143 hasAuthorship W3117488143A5059373349 @default.
- W3117488143 hasAuthorship W3117488143A5060575116 @default.
- W3117488143 hasAuthorship W3117488143A5062939922 @default.
- W3117488143 hasAuthorship W3117488143A5091646587 @default.
- W3117488143 hasBestOaLocation W31174881432 @default.
- W3117488143 hasConcept C110875604 @default.
- W3117488143 hasConcept C11276805 @default.
- W3117488143 hasConcept C119857082 @default.
- W3117488143 hasConcept C121955636 @default.
- W3117488143 hasConcept C136764020 @default.
- W3117488143 hasConcept C147220207 @default.
- W3117488143 hasConcept C153517567 @default.
- W3117488143 hasConcept C154945302 @default.
- W3117488143 hasConcept C162324750 @default.
- W3117488143 hasConcept C163239763 @default.
- W3117488143 hasConcept C175444787 @default.
- W3117488143 hasConcept C195487862 @default.
- W3117488143 hasConcept C41008148 @default.
- W3117488143 hasConcept C512338625 @default.
- W3117488143 hasConceptScore W3117488143C110875604 @default.
- W3117488143 hasConceptScore W3117488143C11276805 @default.
- W3117488143 hasConceptScore W3117488143C119857082 @default.
- W3117488143 hasConceptScore W3117488143C121955636 @default.
- W3117488143 hasConceptScore W3117488143C136764020 @default.
- W3117488143 hasConceptScore W3117488143C147220207 @default.
- W3117488143 hasConceptScore W3117488143C153517567 @default.
- W3117488143 hasConceptScore W3117488143C154945302 @default.
- W3117488143 hasConceptScore W3117488143C162324750 @default.
- W3117488143 hasConceptScore W3117488143C163239763 @default.
- W3117488143 hasConceptScore W3117488143C175444787 @default.
- W3117488143 hasConceptScore W3117488143C195487862 @default.
- W3117488143 hasConceptScore W3117488143C41008148 @default.
- W3117488143 hasConceptScore W3117488143C512338625 @default.
- W3117488143 hasLocation W31174881431 @default.
- W3117488143 hasLocation W31174881432 @default.
- W3117488143 hasOpenAccess W3117488143 @default.
- W3117488143 hasPrimaryLocation W31174881431 @default.
- W3117488143 hasRelatedWork W2140434668 @default.
- W3117488143 hasRelatedWork W2362999972 @default.
- W3117488143 hasRelatedWork W2573821030 @default.
- W3117488143 hasRelatedWork W2738248564 @default.
- W3117488143 hasRelatedWork W3124084175 @default.
- W3117488143 hasRelatedWork W3124825997 @default.
- W3117488143 hasRelatedWork W3126053789 @default.
- W3117488143 hasRelatedWork W3143416514 @default.
- W3117488143 hasRelatedWork W4242054268 @default.
- W3117488143 hasRelatedWork W4360841431 @default.
- W3117488143 isParatext "false" @default.
- W3117488143 isRetracted "false" @default.
- W3117488143 magId "3117488143" @default.
- W3117488143 workType "article" @default.