Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate

ABSTRACT

Estimating post-click conversion rate (CVR) accurately is crucial for ranking systems in industrial applications such as recommendation and advertising. Conventional CVR modeling applies popular deep learning methods and achieves state-of-the-art performance. However it encounters several task-specific problems in practice, making CVR modeling challenging. For example, conventional CVR models are trained with samples of clicked impressions while utilized to make inference on the entire space with samples of all impressions. This causes a sample selection bias problem. Besides, there exists an extreme data sparsity problem, making the model fitting rather difficult. In this paper, we model CVR in a brand-new perspective by making good use of sequential pattern of user actions, i.e., impression -> click -> conversion. The proposed Entire Space Multi-task Model (ESMM) can eliminate the two problems simultaneously by i) modeling CVR directly over the entire space, ii) employing a feature representation transfer learning strategy. Experiments on dataset gathered from Taobao's recommender system demonstrate that ESMM significantly outperforms competitive methods. We also release a sampling version of this dataset to enable future research. To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.

References

1. Heng-Tze Cheng and Levent Koc. 2016. Wide&deep learning for recommender systems. In Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. ACM, 7--10.
2. Zhou G., Song C., et al. 2017. Deep Interest Network for Click-Through Rate Prediction. arXiv preprint arXiv:1706.06978 (2017).
3. Zhu H., Jin J., et al. 2017. Optimized cost per click in taobao display advertising. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2191--2200.
4. Lee K., Orten B., et al. 2012. Estimating conversion rate in display advertising from past erformance data. In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM.
5. Rong Pan, Yunhong Zhou, Bin Cao, Nathan N Liu, Rajan Lukose, Martin Scholz, and Qiang Yang. 2008. One-class collaborative filtering. In Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on. IEEE, 502--511.
6. Sebastian Ruder. 2017. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098 (2017).
7. Zhang W., Zhou T., et al. 2016. Bid-aware gradient descent for unbiased learning with censored data in display advertising. In Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining. ACM.
8. Gary M Weiss. 2004. Mining with rarity: a unifying framework. ACM Sigkdd Explorations Newsletter 6, 1 (2004), 7--19.
9. Bianca Zadrozny. 2004. Learning and evaluating classifiers under sample selection bias. In Proceedings of the 21th international conference on Machine learning. ACM.

Index Terms

• Information systems

  • Information retrieval

    • Retrieval models and ranking

      • Learning to rank