The Estimation of Continual Causal Effect for Dataset Shifting Streams
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913812184039424 |
|---|---|
| author | Chen, Baining Zhang, Yiming Han, Yuqiao Zhang, Ruyue Du, Ruihuan Zhou, Zhishuo Zhu, Zhengdan Liu, Xun Guo, Jiecheng |
| author_facet | Chen, Baining Zhang, Yiming Han, Yuqiao Zhang, Ruyue Du, Ruihuan Zhou, Zhishuo Zhu, Zhengdan Liu, Xun Guo, Jiecheng |
| contents | Causal effect estimation has been widely used in marketing optimization. The framework of an uplift model followed by a constrained optimization algorithm is popular in practice. To enhance performance in the online environment, the framework needs to be improved to address the complexities caused by temporal dataset shift. This paper focuses on capturing the dataset shift from user behavior and domain distribution changing over time. We propose an Incremental Causal Effect with Proxy Knowledge Distillation (ICE-PKD) framework to tackle this challenge. The ICE-PKD framework includes two components: (i) a multi-treatment uplift network that eliminates confounding bias using counterfactual regression; (ii) an incremental training strategy that adapts to the temporal dataset shift by updating with the latest data and protects generalization via replay-based knowledge distillation. We also revisit the uplift modeling metrics and introduce a novel metric for more precise online evaluation in multiple treatment scenarios. Extensive experiments on both simulated and online datasets show that the proposed framework achieves better performance. The ICE-PKD framework has been deployed in the marketing system of Huaxiaozhu, a ride-hailing platform in China. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_20471 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Estimation of Continual Causal Effect for Dataset Shifting Streams Chen, Baining Zhang, Yiming Han, Yuqiao Zhang, Ruyue Du, Ruihuan Zhou, Zhishuo Zhu, Zhengdan Liu, Xun Guo, Jiecheng Machine Learning Artificial Intelligence Methodology Causal effect estimation has been widely used in marketing optimization. The framework of an uplift model followed by a constrained optimization algorithm is popular in practice. To enhance performance in the online environment, the framework needs to be improved to address the complexities caused by temporal dataset shift. This paper focuses on capturing the dataset shift from user behavior and domain distribution changing over time. We propose an Incremental Causal Effect with Proxy Knowledge Distillation (ICE-PKD) framework to tackle this challenge. The ICE-PKD framework includes two components: (i) a multi-treatment uplift network that eliminates confounding bias using counterfactual regression; (ii) an incremental training strategy that adapts to the temporal dataset shift by updating with the latest data and protects generalization via replay-based knowledge distillation. We also revisit the uplift modeling metrics and introduce a novel metric for more precise online evaluation in multiple treatment scenarios. Extensive experiments on both simulated and online datasets show that the proposed framework achieves better performance. The ICE-PKD framework has been deployed in the marketing system of Huaxiaozhu, a ride-hailing platform in China. |
| title | The Estimation of Continual Causal Effect for Dataset Shifting Streams |
| topic | Machine Learning Artificial Intelligence Methodology |
| url | https://arxiv.org/abs/2504.20471 |