Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.14103 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917057443921920 |
|---|---|
| author | Zhang, Xin Li, Weiliang Li, Rui Fu, Zihang Tang, Tongyi Zhang, Zhengyu Chen, Wen-Yen Noorshams, Nima Jasapara, Nirav Ding, Xiaowen Wen, Ellie Feng, Xue |
| author_facet | Zhang, Xin Li, Weiliang Li, Rui Fu, Zihang Tang, Tongyi Zhang, Zhengyu Chen, Wen-Yen Noorshams, Nima Jasapara, Nirav Ding, Xiaowen Wen, Ellie Feng, Xue |
| contents | Optimizing conversions is crucial in modern online advertising systems, enabling advertisers to deliver relevant products to users and drive business outcomes. However, accurately predicting conversion events remains challenging due to variable time delays between user interactions (e.g., impressions or clicks) and the actual conversions. These delays vary substantially across advertisers and products, necessitating flexible optimization windows tailored to specific conversion behaviors. To address this, we propose a novel \textit{Personalized Interpolation} method that extends existing models based on fixed conversion windows to support flexible advertiser-specific optimization windows. Our method enables accurate conversion estimation across diverse delay distributions without increasing system complexity. We evaluate the effectiveness of the proposed approach through extensive experiments using a real-world ads conversion model. Our results show that this method achieves both high prediction accuracy and improved efficiency compared to existing solutions. This study demonstrates the potential of our Personalized Interpolation method to improve conversion optimization and support a wider range of advertising strategies in large-scale online advertising systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_14103 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Personalized Interpolation: Achieving Efficient Conversion Estimation with Flexible Optimization Windows Zhang, Xin Li, Weiliang Li, Rui Fu, Zihang Tang, Tongyi Zhang, Zhengyu Chen, Wen-Yen Noorshams, Nima Jasapara, Nirav Ding, Xiaowen Wen, Ellie Feng, Xue Machine Learning Optimizing conversions is crucial in modern online advertising systems, enabling advertisers to deliver relevant products to users and drive business outcomes. However, accurately predicting conversion events remains challenging due to variable time delays between user interactions (e.g., impressions or clicks) and the actual conversions. These delays vary substantially across advertisers and products, necessitating flexible optimization windows tailored to specific conversion behaviors. To address this, we propose a novel \textit{Personalized Interpolation} method that extends existing models based on fixed conversion windows to support flexible advertiser-specific optimization windows. Our method enables accurate conversion estimation across diverse delay distributions without increasing system complexity. We evaluate the effectiveness of the proposed approach through extensive experiments using a real-world ads conversion model. Our results show that this method achieves both high prediction accuracy and improved efficiency compared to existing solutions. This study demonstrates the potential of our Personalized Interpolation method to improve conversion optimization and support a wider range of advertising strategies in large-scale online advertising systems. |
| title | Personalized Interpolation: Achieving Efficient Conversion Estimation with Flexible Optimization Windows |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.14103 |