Counterfactual Evaluation of Ads Ranking Models through Domain Adaptation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| 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 |