Estimated Time of package Arrival (ETA) is an essential task for Alibaba E-commerce platforms like Taobao and Tmall, which may influence the user experiences of one billion customers. The main challenge in ETA prediction of Alibaba platforms is learning from high-dimensional categorical attributes, which is equally important to obtain appropriate representations for each feature, and describe the proximity among them. Although recent supervised end-to-end methods have achieved great improvements, the unsupervised embedding method for categorical attributes has not been well-studied yet, especially when dealing with large-scale sparse datasets.

The ability to predict future customer orders is of significant value to retailers in making many crucial operational decisions. Different from next basket prediction or temporal set prediction, which focuses on predicting a subset of items for a single user, this paper aims for the distributional information of future orders, i.e., the possible subsets of items and their frequencies (probabilities), which is required for decisions such as assortment selection for front-end warehouses and capacity evaluation for fulfillment centers. Based on key statistics of a real order dataset from Tmall supermarket, we show the challenges of order prediction. Motivated by our analysis that biased models of order distribution can still help improve the quality of order prediction, we design a generative model to capture the order distribution for customer order prediction. Our model utilizes representation learning to embed items into a Euclidean space and design a highly efficient SGD algorithm to learn the item embeddings. Future order prediction is done by calibrating orders obtained by random walks over the embedding graph. The experiments show that our model outperforms all the existing methods. The benefit of our model is also illustrated with an application to assortment selection for front-end warehouses.

We propose two recommendation algorithms for e-commerce with supply limits, a scenario that has not been intensively studied in the literature. One algorithm is a linear programming-based algorithm that uses historical data to approximate customer arrival patterns and generate shadow prices for inventories. The price of inventory can be introduced to existing recommendation algorithms to obtain adjusted rankings for recommendation. The other algorithm balances expected revenue and inventory consumption, and it uses a simple penalty function to reduce the chance of recommending low-inventory-level products. Both algorithms are suitable for online recommendation systems for grocery stores with both online and offline channels, and can incorporate the features of perishable products, which need to be sold within limited time. Both algorithms are tested in a simulation using estimated parameters from Freshippo, a supermarket owned by the Alibaba Group. The numerical results show that both algorithms can generate higher sales volume and higher revenue.

The presence or absence of one item in a recommendation list will affect the demand for other items because customers are often willing to switch to other items if their most preferred items are not available. The cross-item influence, called “peers effect”, has been largely ignored in the literature. In this paper, we develop a peers-aware recommender system, named PARS. We apply a ranking-based choice model to capture the cross-item influence and solve the resultant MaxMin problem with a decomposition algorithm. The MaxMin model solves for the recommendation decision in the meanwhile of estimating users’ preferences towards the items, which yields high-quality recommendations robust to input data variation. Experimental results illustrate that PARS outperforms a few frequently used methods in practice. An online evaluation with a flash sales scenario at Taobao also shows that PARS delivers significant improvements in terms of both conversion rates and user value.

Product sales forecasting plays a fundamental role in enhancing timeliness of product delivery in E-Commerce. Among many heterogeneous features relevant to sales forecasting, promotion campaigns held in E-Commerce and competing relation between substitutable products would greatly complicate the matter. Unfortunately, these factors are usually overlooked in the existing literature, since the conventional time series analysis based techniques mainly consider the sales records alone. In this paper, we propose a novel deep neural framework for sales forecasting in E-Commerce, named DSF. In DSF, sales forecasting is formulated as a sequence-to-sequence learning problem where the sales is estimated in a recurrent fashion. On top of the decoder, we introduce a sales residual network to explicitly model the impact of competing relation when a promotion campaign is launched for a target item or some substitutable counterparts. Extensive experiments are conducted over two real-world datasets in different domains from Taobao E-Commerce platform. Our results demonstrate that the proposed DSF obtains substantial performance gain over the traditional baselines and up-to-date deep learning alternatives in terms of forecasting accuracy. Further comparison shows that DSF has also surpassed the deep learning based solution currently depolyed in Taobao platform.

Supply chain management (SCM) is fundamental for gaining financial, environmental and social benefits in the supply chain industry. However, traditional SCM mechanisms usually suffer from a wide scope of issues such as lack of information sharing, long delays for data retrieval, and unreliability in product tracing. Recent advances in blockchain technology show great potential to tackle these issues due to its salient features including immutability, transparency, and decentralization. Although there are some proof-of-concept studies and surveys on blockchain-based SCM from the perspective of logistics, the underlying technical challenges are not clearly identified. In this paper, we provide a comprehensive analysis of potential opportunities, new requirements, and principles of designing blockchain-based SCM systems. We summarize and discuss four crucial technical challenges in terms of scalability, throughput, access control, data retrieval and review the promising solutions. Finally, a case study of designing blockchain-based food traceability system is reported to provide more insights on how to tackle these technical challenges in practice.

International audience

User reviews contain rich semantics towards the preference of users to features of items. Recently, many deep learning based solutions have been proposed by exploiting reviews for recommendation. The attention mechanism is mainly adopted in these works to identify words or aspects that are important for rating prediction. However, it is still hard to understand whether a user likes or dislikes an aspect of an item according to what viewpoint the user holds and to what extent, without examining the review details. Here, we consider a pair of a viewpoint held by a user and an aspect of an item as a logic unit. Reasoning a rating behavior by discovering the informative logic units from the reviews and resolving their corresponding sentiments could enable a better rating prediction with explanation.