Delayed Feedback Modeling with Influence Functions
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915445374713856 |
|---|---|
| author | Ding, Chenlu Wu, Jiancan Yuan, Yancheng Li, Cunchun Wang, Xiang Wang, Dingxian Yang, Frank Rabinovich, Andrew |
| author_facet | Ding, Chenlu Wu, Jiancan Yuan, Yancheng Li, Cunchun Wang, Xiang Wang, Dingxian Yang, Frank Rabinovich, Andrew |
| contents | In online advertising under the cost-per-conversion (CPA) model, accurate conversion rate (CVR) prediction is crucial. A major challenge is delayed feedback, where conversions may occur long after user interactions, leading to incomplete recent data and biased model training. Existing solutions partially mitigate this issue but often rely on auxiliary models, making them computationally inefficient and less adaptive to user interest shifts. We propose IF-DFM, an \underline{I}nfluence \underline{F}unction-empowered for \underline{D}elayed \underline{F}eedback \underline{M}odeling which estimates the impact of newly arrived and delayed conversions on model parameters, enabling efficient updates without full retraining. By reformulating the inverse Hessian-vector product as an optimization problem, IF-DFM achieves a favorable trade-off between scalability and effectiveness. Experiments on benchmark datasets show that IF-DFM outperforms prior methods in both accuracy and adaptability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01669 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Delayed Feedback Modeling with Influence Functions Ding, Chenlu Wu, Jiancan Yuan, Yancheng Li, Cunchun Wang, Xiang Wang, Dingxian Yang, Frank Rabinovich, Andrew Machine Learning Artificial Intelligence Information Retrieval In online advertising under the cost-per-conversion (CPA) model, accurate conversion rate (CVR) prediction is crucial. A major challenge is delayed feedback, where conversions may occur long after user interactions, leading to incomplete recent data and biased model training. Existing solutions partially mitigate this issue but often rely on auxiliary models, making them computationally inefficient and less adaptive to user interest shifts. We propose IF-DFM, an \underline{I}nfluence \underline{F}unction-empowered for \underline{D}elayed \underline{F}eedback \underline{M}odeling which estimates the impact of newly arrived and delayed conversions on model parameters, enabling efficient updates without full retraining. By reformulating the inverse Hessian-vector product as an optimization problem, IF-DFM achieves a favorable trade-off between scalability and effectiveness. Experiments on benchmark datasets show that IF-DFM outperforms prior methods in both accuracy and adaptability. |
| title | Delayed Feedback Modeling with Influence Functions |
| topic | Machine Learning Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2502.01669 |