Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.12468 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913700186685440 |
|---|---|
| author | Dou, Bin Wang, Baokun Zhu, Yun Lin, Xiaotong Xu, Yike Huang, Xiaorui Chen, Yang Liu, Yun Han, Shaoshuai Liu, Yongchao Zhang, Tianyi Cheng, Yu Wang, Weiqiang Hong, Chuntao |
| author_facet | Dou, Bin Wang, Baokun Zhu, Yun Lin, Xiaotong Xu, Yike Huang, Xiaorui Chen, Yang Liu, Yun Han, Shaoshuai Liu, Yongchao Zhang, Tianyi Cheng, Yu Wang, Weiqiang Hong, Chuntao |
| contents | User targeting, the process of selecting targeted users from a pool of candidates for non-expert marketers, has garnered substantial attention with the advancements in digital marketing. However, existing user targeting methods encounter two significant challenges: (i) Poor cross-domain and cross-scenario transferability and generalization, and (ii) Insufficient forecastability in real-world applications. These limitations hinder their applicability across diverse industrial scenarios. In this work, we propose FOUND, an industrial-grade, transferable, and forecastable user targeting foundation model. To enhance cross-domain transferability, our framework integrates heterogeneous multi-scenario user data, aligning them with one-sentence targeting demand inputs through contrastive pre-training. For improved forecastability, the text description of each user is derived based on anticipated future behaviors, while user representations are constructed from historical information. Experimental results demonstrate that our approach significantly outperforms existing baselines in cross-domain, real-world user targeting scenarios, showcasing the superior capabilities of FOUND. Moreover, our method has been successfully deployed on the Alipay platform and is widely utilized across various scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12468 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transferable and Forecastable User Targeting Foundation Model Dou, Bin Wang, Baokun Zhu, Yun Lin, Xiaotong Xu, Yike Huang, Xiaorui Chen, Yang Liu, Yun Han, Shaoshuai Liu, Yongchao Zhang, Tianyi Cheng, Yu Wang, Weiqiang Hong, Chuntao Machine Learning Artificial Intelligence User targeting, the process of selecting targeted users from a pool of candidates for non-expert marketers, has garnered substantial attention with the advancements in digital marketing. However, existing user targeting methods encounter two significant challenges: (i) Poor cross-domain and cross-scenario transferability and generalization, and (ii) Insufficient forecastability in real-world applications. These limitations hinder their applicability across diverse industrial scenarios. In this work, we propose FOUND, an industrial-grade, transferable, and forecastable user targeting foundation model. To enhance cross-domain transferability, our framework integrates heterogeneous multi-scenario user data, aligning them with one-sentence targeting demand inputs through contrastive pre-training. For improved forecastability, the text description of each user is derived based on anticipated future behaviors, while user representations are constructed from historical information. Experimental results demonstrate that our approach significantly outperforms existing baselines in cross-domain, real-world user targeting scenarios, showcasing the superior capabilities of FOUND. Moreover, our method has been successfully deployed on the Alipay platform and is widely utilized across various scenarios. |
| title | Transferable and Forecastable User Targeting Foundation Model |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.12468 |