Learning Tree-based Deep Model for Recommender Systems

Abstract

Large-scale industrial recommender systems are usually confronted with computational problems due to the enormous corpus size. To retrieve and recommend the most relevant items to users under response time limits, resorting to an efficient index structure is an effective and practical solution. The previous work Tree-based Deep Model (TDM) [34] greatly improves recommendation accuracy using tree index. By indexing items in a tree hierarchy and training a user-node preference prediction model satisfying a max-heap like property in the tree, TDM provides logarithmic computational complexity w.r.t. the corpus size, enabling the use of arbitrary advanced models in candidate retrieval and recommendation. In tree-based recommendation methods, the quality of both the tree index and the user-node preference prediction model determines the recommendation accuracy for the most part. We argue that the learning of tree index and preference model has interdependence. Our purpose, in this paper, is to develop a method to jointly learn the index structure and user preference prediction model. In our proposed joint optimization framework, the learning of index and user preference prediction model are carried out under a unified performance measure. Besides, we come up with a novel hierarchical user preference representation utilizing the tree index hierarchy. Experimental evaluations with two large-scale real-world datasets show that the proposed method improves recommendation accuracy significantly.

Behavior sequence transformer for e-commerce recommendation in Alibaba

“…During the last decade, Recommender Systems (RSs) have been the most popular application in industry, and in the past five years, deep learning based methods have been widely used in industrial RSs, e.g., Google [2,3] and Airbnb [5]. In Alibaba, the largest ecommerce platform in China, RSs have been the key engine for its Gross Merchandise Volume (GMV) and revenues, and various deep learning based recommendation methods have been deployed in rich e-commerce scenarios [1,8,10,11,14,15,17,18]. As introduced in [15], the RSs in Alibaba are a two-stage pipeline: match and rank.…”

Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction

“…This processing method has been widely used in the related works [60,61]. Taobao [62] is a dataset of user behaviors from the commercial platform of Taobao. The dataset contains several types of user behaviors including click, purchase, add-to-cart and item favoring.…”

SDM

“…The prediction is made as equivalent to search the nearest neighbors of users' vectors among all the items. Besides, Zhu et al [34] proposes a novel tree-based large-scale recommender system, which can provide novel items and overcome the calculation barrier of vector search. Recently, graph embedding based methods are applied in many industrial applications to complement or replace traditional methods.…”