Recommender systems (RSs) have been the most important technology for increasing the business in Taobao, the largest online consumer-to-consumer (C2C) platform in China. There are three major challenges facing RS in Taobao: scalability, sparsity and cold start. In this paper, we present our technical solutions to address these three challenges. The methods are based on a wellknown graph embedding framework. We first construct an item graph from users' behavior history, and learn the embeddings of all items in the graph. The item embeddings are employed to compute pairwise similarities between all items, which are then used in the recommendation process. To alleviate the sparsity and cold start problems, side information is incorporated into the graph embedding framework. We propose two aggregation methods to integrate the embeddings of items and the corresponding side information. Experimental results from offline experiments show that methods incorporating side information are superior to those that do not. Further, we describe the platform upon which the embedding methods are deployed and the workflow to process the billion-scale data in Taobao. Using A/B test, we show that the online Click-Through-Rates (CTRs) are improved comparing to the previous collaborative filtering based methods widely used in Taobao, further demonstrating the effectiveness and feasibility of our proposed methods in Taobao's live production environment.

Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves candidate items relevant to user interests, while the ranking stage sorts candidate items by user interests. Thus, the most critical ability is to model and represent user interests for either stage. Most of the existing deep learning-based models represent one user as a single vector which is insufficient to capture the varying nature of user's interests. In this paper, we approach this problem from a different view, to represent one user with multiple vectors encoding the different aspects of the user's interests. We propose the Multi-Interest Network with Dynamic routing (MIND) for dealing with user's diverse interests in the matching stage. Specifically, we design a multi-interest extractor layer based on capsule routing mechanism, which is applicable for clustering historical behaviors and extracting diverse interests. Furthermore, we develop a technique named label-aware attention to help learn a user representation with multiple vectors. Through extensive experiments on several public benchmarks and one largescale industrial dataset from Tmall, we demonstrate that MIND can achieve superior performance than state-of-the-art methods for recommendation. Currently, MIND has been deployed for handling major online traffic at the homepage on Mobile Tmall App.

Deep learning based methods have been widely used in industrial recommendation systems (RSs). Previous works adopt an Em-bedding&MLP paradigm: raw features are embedded into lowdimensional vectors, which are then fed on to MLP for final recommendations. However, most of these works just concatenate different features, ignoring the sequential nature of users' behaviors. In this paper, we propose to use the powerful Transformer model to capture the sequential signals underlying users' behavior sequences for recommendation in Alibaba. Experimental results demonstrate the superiority of the proposed model, which is then deployed online at Taobao and obtain significant improvements in online Click-Through-Rate (CTR) comparing to two baselines.

Increasing demand for fashion recommendation raises a lot of challenges for online shopping platforms and fashion communities. In particular, there exist two requirements for fashion out t recommendation: the Compatibility of the generated fashion out ts, and the Personalization in the recommendation process. In this paper, we demonstrate these two requirements can be satis ed via building a bridge between out t generation and recommendation. rough large data analysis, we observe that people have similar tastes in individual items and out ts. erefore, we propose a Personalized Out t Generation (POG) model, which connects user preferences regarding individual items and out ts with Transformer architecture. Extensive o ine and online experiments provide strong quantitative evidence that our method outperforms alternative methods regarding both compatibility and personalization metrics. Furthermore, we deploy POG on a platform named Dida in Alibaba to generate personalized out ts for the users of the online application iFashion.is work represents a rst step towards an industrial-scale fashion out t generation and recommendation solution, which goes beyond generating out ts based on explicit queries, or merely recommending from existing out t pools. As part of this work, we release a large-scale dataset consisting of 1.01 million out ts with rich context information, and 0.28 billion user click actions from 3.57 million users. To the best of our knowledge, this dataset is the largest, publicly available, fashion related dataset, and the rst to provide user behaviors relating to both out ts and fashion items.

No abstract