Hierarchical User Profiling for E-commerce Recommender Systems

Gu, Yun; Ding, Zhuoye; Wang, Shuaiqiang; Yin, Dawei

doi:10.1145/3336191.3371827

Cited by 73 publications

(42 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They can be regarded as complement work with our approach. State-of-the-art methods have found the effectiveness of modeling users' historical behaviors for CTR prediction [8,10,16,17,26,27,31,40,41]. DIN [41] notices that a user may have multiple interests and uses attention mechanism to learn the representation of user interests from historical behaviors with respect to a certain candidate item.…”

Section: Related Work 21 Ctr Predictionmentioning

confidence: 99%

“…Recommender Systems, which aim to recommend potentially interested items for users and solve the information explosion problem, are playing critical roles in E-commerce sites (e.g., Amazon, JD.com, Alibaba) [10,20,41,42], videos sharing sites (e.g., YouTube) [7], picture sharing sites (e.g., Pinterest) [36], social networks (e.g., Facebook) [11,13] and so on. For example, in JD.com, one of the largest E-commerce sites in the world, the Recommender System serves more than 0.3 billion users in China, Thailand, Malaysia and other countries, and contributes billions of dollars for the Gross Merchandise Volume (GMV) (i.e., the total sales value for merchandise sold) each year.…”

Section: Introductionmentioning

confidence: 99%

“…Many ranking methods for recommendations have been proposed, including tree-based methods [9], deep neural networks [5,7,10,40,41], reinforcement learning [42,43] based models and so on. However, designing a real-world large-scale E-commerce recommender system still faces many challenges, including:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Multifaceted Transformers for Multi-objective Ranking in Large-Scale E-commerce Recommender Systems

Ding

Wang

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

Recommender Systems have been playing essential roles in ecommerce portals. Existing recommendation algorithms usually learn the ranking scores of items by optimizing a single task (e.g., Click-through rate prediction) based on users' historical click sequences, but they generally pay few attention to simultaneously modeling users' multiple types of behaviors or jointly optimize multiple objectives (e.g., both Click-through rate and Conversion rate), which are both vital for e-commerce sites. In this paper, we argue that it is crucial to formulate users' different interests based on multiple types of behaviors and perform multi-task learning for significant improvement in multiple objectives simultaneously. We propose Deep Multifaceted Transformers (DMT), a novel framework that can model users' multiple types of behavior sequences simultaneously with multiple Transformers. It utilizes Multi-gate Mixture-of-Experts to optimize multiple objectives. Besides, it exploits unbiased learning to reduce the selection bias in the training data. Experiments on JD real production dataset demonstrate the effectiveness of DMT, which significantly outperforms state-ofart methods. DMT has been successfully deployed to serve the main traffic in the commercial Recommender System in JD.com. To facilitate future research, we release the codes and datasets at https://github.com/guyulongcs/CIKM2020_DMT.

show abstract

Section: Related Work 21 Ctr Predictionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Multifaceted Transformers for Multi-objective Ranking in Large-Scale E-commerce Recommender Systems

Ding

Wang

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

View full text Add to dashboard Cite

show abstract

“…Compared to item representations which are usually refined using various specially designed models, in most previous work [17,18,21,30], user preferences are often learned in a similar way with a trainable embedding matrix. In addition, several researchers further apply attention mechanism to help learn user preferences [12,13,34,35].…”

Section: Representation Learningmentioning

confidence: 99%

“…Apart from item representations and user preferences, various types of interaction data are also utilized by researchers to train models [11,13,28,35]. Among those attempts to learn from interactions, there is a kind of methods based on graph-based neural networks achieves great success.…”

Section: Representation Learningmentioning

confidence: 99%

Personalized Item Recommendation for Second-hand Trading Platform

Gan

Wei

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

With rising awareness of environment protection and recycling, secondhand trading platforms have attracted increasing attention in recent years. The interaction data on secondhand trading platforms, consisting of sufficient interactions per user but rare interactions per item, is different from what they are on traditional platforms. Therefore, building successful recommendation systems in the secondhand trading platforms requires balancing modeling items' and users' preference, and mitigating the adverse effects of the sparsity, which makes recommendation especially challenging. Accordingly, we proposed a method to simultaneously learn representations of items and users from coarse-grained and fine-grained features, and a multi-task learning strategy is designed to address the issue of data sparsity. Experiments conducted on a real-world secondhand trading platform dataset demonstrate the effectiveness of our proposed model.

show abstract