Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Radwan, Mohamed A., Bhattacharjee, Himaghna, Lanners, Quinn, Zhang, Jiasheng, Karakulak, Serkan, Nassif, Houssam, Bayir, Murat Ali
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909425077321728
author Radwan, Mohamed A.
Bhattacharjee, Himaghna
Lanners, Quinn
Zhang, Jiasheng
Karakulak, Serkan
Nassif, Houssam
Bayir, Murat Ali
author_facet Radwan, Mohamed A.
Bhattacharjee, Himaghna
Lanners, Quinn
Zhang, Jiasheng
Karakulak, Serkan
Nassif, Houssam
Bayir, Murat Ali
contents We propose a domain-adapted reward model that works alongside an Offline A/B testing system for evaluating ranking models. This approach effectively measures reward for ranking model changes in large-scale Ads recommender systems, where model-free methods like IPS are not feasible. Our experiments demonstrate that the proposed technique outperforms both the vanilla IPS method and approaches using non-generalized reward models.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19824
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation
Radwan, Mohamed A.
Bhattacharjee, Himaghna
Lanners, Quinn
Zhang, Jiasheng
Karakulak, Serkan
Nassif, Houssam
Bayir, Murat Ali
Information Retrieval
Artificial Intelligence
H.3.3; I.2.6
We propose a domain-adapted reward model that works alongside an Offline A/B testing system for evaluating ranking models. This approach effectively measures reward for ranking model changes in large-scale Ads recommender systems, where model-free methods like IPS are not feasible. Our experiments demonstrate that the proposed technique outperforms both the vanilla IPS method and approaches using non-generalized reward models.
title Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation
topic Information Retrieval
Artificial Intelligence
H.3.3; I.2.6
url https://arxiv.org/abs/2409.19824