The query-based recommendation now is becoming a basic research topic in the e-commerce scenario. Generally, given a query that a user typed, it aims to provide a set of items that the user may be interested in. In this task, the customer intention (i.e., browsing or purchase) is an important factor to configure the corresponding recommendation strategy for better shopping experiences (i.e., providing diverse items when the user prefers to browse or recommending specific items when detecting the user is willing to purchase). Though necessary, this is usually overlooked in previous works. In addition, the diversity and evolution of user interests also bring challenges to inferring user intentions correctly.

Multi-scenario Learning to Rank is essential for Recommender Systems, Search Engines and Online Advertising in e-commerce portals where the ranking models are usually applied in many scenarios. However, existing works mainly focus on learning the ranking model for a single scenario, and pay less attention to learning ranking models for multiple scenarios. We identify two practical challenges in industrial multi-scenario ranking systems: (1) The Feedback Loop problem that the model is always trained on the items chosen by the ranker itself. (2) Insufficient training data for small and new scenarios. To address the above issues, we present ZEUS, a novel framework that learns a Zoo of ranking modEls for mUltiple Scenarios based on pre-training on users' spontaneous behaviors (e.g. queries which are directly searched in the search box and not recommended by the ranking system). ZEUS decomposes the training process into two stages: self-supervised learning based pre-training and fine-tuning. Firstly, ZEUS performs self-supervised learning on users' spontaneous behaviors and generates a pre-trained model. Secondly, ZEUS fine-tunes the pre-trained model on users' implicit feedback in multiple scenarios. Extensive experiments on Alibaba's production dataset demonstrate the effectiveness of ZEUS, which significantly outperforms state-of-the-art methods. ZEUS averagely achieves 6.0%, 9.7%, 11.7% improvement in CTR, CVR and GMV respectively than state-of-the-art method.

Intent recommendation, as a new type of recommendation service, is to recommend a predicted query to a user in the search box when the user lands on the homepage of an application without any input. Such an intent recommendation service has been widely used in e-commerce applications, such as Taobao and Amazon. The most difficult part is to accurately predict user’s search intent, so as to improve user’s search experience and reduce tedious typing especially on mobile phones. Existing methods mainly rely on user’s historical search behaviors to estimate user’s current intent, but they do not make full use of the feedback information between the user and the intent recommendation system. Essentially, feedback information is the key factor for capturing dynamics of user search intents in real time. Therefore, we propose a feedback interactive neural network (FINN) to estimate user’s potential search intent more accurately, by making full use of the feedback interaction with the following three parts: 1) Both positive feedback (PF) and negative feedback (NF) information are collected simultaneously. PF includes user’s search intent information that the user is interested in, such as the query used and the title clicked. NF indicates user’s search intent information that the user is not interested in, such as the query recommended by the system but not clicked by the user. 2) A filter-attention (FAT) structure is proposed to filter out the noisy feedback and get more accurate positive and negative intentions of users. 3) A multi-task learning is designed to match the correlation between the user’s search intent and query candidates, which can learn and recommend query candidates from user interests and disinterests associated with each user. Finally, extensive experiments have been conducted by comparing with state-of-the-art methods, and it shows that our FINN method can achieve the best performance using the Taobao mobile application dataset. In addition, online experimental results also show that our method improves the CTR by 8% and attracts more than 7.98% of users than the baseline.

With the prevalence of mobile e-commerce nowadays, a new type of recommendation services, called intent recommendation, is widely used in many mobile e-commerce Apps, such as Taobao and Amazon. Different from traditional query recommendation and item recommendation, intent recommendation is to automatically recommend user intent according to user historical behaviors without any input when users open the App. Intent recommendation becomes very popular in the past two years, because of revealing user latent intents and avoiding tedious input in mobile phones. Existing methods used in industry usually need laboring feature engineering. Moreover, they only utilize attribute and statistic information of users and queries, and fail to take full advantage of rich interaction information in intent recommendation, which may result in limited performances. In this paper, we propose to model the complex objects and rich interactions in intent recommendation as a Heterogeneous Information Network. Furthermore, we present a novel M etapath-guided E mbedding method for I ntent Rec ommendation~(called MEIRec). In order to fully utilize rich structural information, we design a metapath-guided heterogeneous Graph Neural Network to learn the embeddings of objects in intent recommendation. In addition, in order to alleviate huge learning parameters in embeddings, we propose a uniform term embedding mechanism, in which embeddings of objects are made up with the same term embedding space. Offline experiments on real large-scale data show the superior performance of the proposed MEIRec, compared to representative methods.Moreover, the results of online experiments on Taobao e-commerce platform show that MEIRec not only gains a performance improvement of 1.54% on CTR metric, but also attracts up to 2.66% of new users to search queries.