Matches in SemOpenAlex for { <https://semopenalex.org/work/W4207046351> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4207046351 abstract "Online display advertising has become a vital business for large-scale E-commerce markets. As the main goal of advertisers is to reach interested customer prospects, accurate conversion prediction is essential for successful online display advertising. A particular challenge for conversion prediction is that conversions may occur long after the click events. Such delayed feedback makes it a non-trivial task to keep conversion prediction models updated and consistent with the latest customer distribution. Although several studies have been conducted to tackle the delayed feedback issue, the relationship between the early conversion and full term conversion has not been fully exploited to improve conversion prediction. In this paper, we consider conversion prediction as a multi-task learning problem by leveraging multiple conversion labels after different observation intervals. Specifically, we propose a multi-task model with an end-to-end architecture for conversion prediction. Our approach is guided by theoretical and probabilistic analysis of the early and full term conversions. Our mixture-of-experts module can integrate distinct characteristics of input features and optimize the task-specific experts. In addition, the multiple tasks are jointly learned with a regularization term to ensure the embedding consistency between tasks and prevent potential overfitting issues. In comparison with competitive benchmarks, our approach can significantly improve conversion prediction with delayed feedback and improve business performance of online display advertising." @default.
- W4207046351 created "2022-01-26" @default.
- W4207046351 creator A5016608367 @default.
- W4207046351 creator A5017140258 @default.
- W4207046351 creator A5018868194 @default.
- W4207046351 creator A5033864788 @default.
- W4207046351 creator A5064896127 @default.
- W4207046351 date "2021-12-01" @default.
- W4207046351 modified "2023-09-28" @default.
- W4207046351 title "Conversion Prediction with Delayed Feedback: A Multi-task Learning Approach" @default.
- W4207046351 cites W1554763265 @default.
- W4207046351 cites W2012905273 @default.
- W4207046351 cites W2021866613 @default.
- W4207046351 cites W2066334462 @default.
- W4207046351 cites W2117030594 @default.
- W4207046351 cites W2511146301 @default.
- W4207046351 cites W2604662567 @default.
- W4207046351 cites W2809290718 @default.
- W4207046351 cites W2893085659 @default.
- W4207046351 cites W2913340405 @default.
- W4207046351 cites W2951369132 @default.
- W4207046351 cites W2962989965 @default.
- W4207046351 cites W2973172293 @default.
- W4207046351 cites W2973198305 @default.
- W4207046351 cites W3035596828 @default.
- W4207046351 cites W3087931390 @default.
- W4207046351 cites W3110889227 @default.
- W4207046351 cites W4297971002 @default.
- W4207046351 doi "https://doi.org/10.1109/icdm51629.2021.00029" @default.
- W4207046351 hasPublicationYear "2021" @default.
- W4207046351 type Work @default.
- W4207046351 citedByCount "0" @default.
- W4207046351 crossrefType "proceedings-article" @default.
- W4207046351 hasAuthorship W4207046351A5016608367 @default.
- W4207046351 hasAuthorship W4207046351A5017140258 @default.
- W4207046351 hasAuthorship W4207046351A5018868194 @default.
- W4207046351 hasAuthorship W4207046351A5033864788 @default.
- W4207046351 hasAuthorship W4207046351A5064896127 @default.
- W4207046351 hasConcept C119857082 @default.
- W4207046351 hasConcept C121332964 @default.
- W4207046351 hasConcept C154945302 @default.
- W4207046351 hasConcept C162324750 @default.
- W4207046351 hasConcept C187736073 @default.
- W4207046351 hasConcept C22019652 @default.
- W4207046351 hasConcept C2776135515 @default.
- W4207046351 hasConcept C2776436953 @default.
- W4207046351 hasConcept C2780451532 @default.
- W4207046351 hasConcept C41008148 @default.
- W4207046351 hasConcept C41608201 @default.
- W4207046351 hasConcept C49937458 @default.
- W4207046351 hasConcept C50644808 @default.
- W4207046351 hasConcept C61797465 @default.
- W4207046351 hasConcept C62520636 @default.
- W4207046351 hasConceptScore W4207046351C119857082 @default.
- W4207046351 hasConceptScore W4207046351C121332964 @default.
- W4207046351 hasConceptScore W4207046351C154945302 @default.
- W4207046351 hasConceptScore W4207046351C162324750 @default.
- W4207046351 hasConceptScore W4207046351C187736073 @default.
- W4207046351 hasConceptScore W4207046351C22019652 @default.
- W4207046351 hasConceptScore W4207046351C2776135515 @default.
- W4207046351 hasConceptScore W4207046351C2776436953 @default.
- W4207046351 hasConceptScore W4207046351C2780451532 @default.
- W4207046351 hasConceptScore W4207046351C41008148 @default.
- W4207046351 hasConceptScore W4207046351C41608201 @default.
- W4207046351 hasConceptScore W4207046351C49937458 @default.
- W4207046351 hasConceptScore W4207046351C50644808 @default.
- W4207046351 hasConceptScore W4207046351C61797465 @default.
- W4207046351 hasConceptScore W4207046351C62520636 @default.
- W4207046351 hasLocation W42070463511 @default.
- W4207046351 hasOpenAccess W4207046351 @default.
- W4207046351 hasPrimaryLocation W42070463511 @default.
- W4207046351 hasRelatedWork W1984730772 @default.
- W4207046351 hasRelatedWork W1996541855 @default.
- W4207046351 hasRelatedWork W2985459377 @default.
- W4207046351 hasRelatedWork W2989932438 @default.
- W4207046351 hasRelatedWork W3011996705 @default.
- W4207046351 hasRelatedWork W3099765033 @default.
- W4207046351 hasRelatedWork W3175189414 @default.
- W4207046351 hasRelatedWork W4210794429 @default.
- W4207046351 hasRelatedWork W4213073923 @default.
- W4207046351 hasRelatedWork W4224929651 @default.
- W4207046351 isParatext "false" @default.
- W4207046351 isRetracted "false" @default.
- W4207046351 workType "article" @default.