Smart Fast Finish: Preventing Overdelivery via Daily Budget Pacing at DoorDash
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912579140452352 |
|---|---|
| author | Garg, Rohan Xiao, Yongjin Jason Yang Rahurkar, Mandar |
| author_facet | Garg, Rohan Xiao, Yongjin Jason Yang Rahurkar, Mandar |
| contents | We present a budget pacing feature called Smart Fast Finish (SFF). SFF builds upon the industry standard Fast Finish (FF) feature in budget pacing systems that depletes remaining advertising budget as quickly as possible towards the end of some fixed time period. SFF dynamically updates system parameters such as start time and throttle rate depending on historical ad-campaign data. SFF is currently in use at DoorDash, one of the largest delivery platforms in the US, and is part of its budget pacing system. We show via online budget-split experimentation data and offline simulations that SFF is a robust solution for overdelivery mitigation when pacing budget. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_07929 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Smart Fast Finish: Preventing Overdelivery via Daily Budget Pacing at DoorDash Garg, Rohan Xiao, Yongjin Jason Yang Rahurkar, Mandar Computer Science and Game Theory Information Retrieval Machine Learning We present a budget pacing feature called Smart Fast Finish (SFF). SFF builds upon the industry standard Fast Finish (FF) feature in budget pacing systems that depletes remaining advertising budget as quickly as possible towards the end of some fixed time period. SFF dynamically updates system parameters such as start time and throttle rate depending on historical ad-campaign data. SFF is currently in use at DoorDash, one of the largest delivery platforms in the US, and is part of its budget pacing system. We show via online budget-split experimentation data and offline simulations that SFF is a robust solution for overdelivery mitigation when pacing budget. |
| title | Smart Fast Finish: Preventing Overdelivery via Daily Budget Pacing at DoorDash |
| topic | Computer Science and Game Theory Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2509.07929 |