Accelerating Ranking in E-Commerce Search Engines through Contextual Factor Selection

Abstract

In large-scale search systems, the quality of the ranking results is continually improved with the introduction of more factors from complex procedures. Meanwhile, the increase in factors demands more computation resources and increases system response latency. It has been observed that, under some certain context a search instance may require only a small set of useful factors instead of all factors in order to return high quality results. Therefore, removing ineffective factors accordingly can significantly improve system efficiency. In this paper, we report our experience incorporating our Contextual Factor Selection (CFS) approach into the Taobao e-commerce platform to optimize the selection of factors based on the context of each search query in order to simultaneously achieve high quality search results while significantly reducing latency time. This problem is treated as a combinatorial optimization problem which can be tackled through a sequential decision-making procedure. The problem can be efficiently solved by CFS through a deep reinforcement learning method with reward shaping to address the problems of reward signal scarcity and wide reward signal distribution in real-world search engines. Through extensive off-line experiments based on data from the Taobao.com platform, CFS is shown to significantly outperform state-of-the-art approaches. Online deployment on Taobao.com demonstrated that CFS is able to reduce average search latency time by more than 40% compared to the previous approach with negligible reduction in search result quality. Under peak usage during the Single's Day Shopping Festival (November 11th) in 2017, CFS reduced peak load search latency time by 33% compared to the previous approach, helping Taobao.com achieve 40% higher revenue than the same period during 2016.

Improved Double‐Layer Structure Multilabel Classification Model via Optimal Sequence and Attention Mechanism

“…show the performance comparison among ATDCC-OS, DLMC, MBR, CC, and BR algorithms, using mean accuracy, coverage metric, single error metric, ranking loss metric, and microaverage AUC metric. We use the metric of the mean ranking (Ave. rank) parameter to review diferent classifcation results of the algorithms [53]. In these fgures, each color represents an algorithm and the name of the algorithm has been listed in the upper left corner of the graph.…”

Optimization of Personalized Recommendation Strategy for E-commerce Platform Based on Artificial Intelligence

“…Where 𝑓) represents the similarity between user 𝐼 and user 𝑓, 𝑂(𝑖) and 𝑂(𝑓) represent the set of products selected by user 𝑖 and user respectively, 𝑅 𝑖𝑗 and 𝑅 𝑓𝑗 represent the scoring (evaluation) of product 𝑗 by user 𝑖 and user 𝑓 respectively, and 𝑅 𝑖 ̅ and 𝑅 𝑓 ̅̅̅ represent the average score of all products by user 𝑖 and user 𝑓 respectively [30]. Jackard correlation coefficient was originally used to measure the similarity between two sets, which was defined as the ratio of the intersection of sets to the union of sets.…”

Enhancing E-commerce Recommender System Adaptability with Online Deep Controllable Learning-To-Rank

“…After slight adjustments by scattering and re-ranking, the resulting item list was returned to user's applications (e.g., mobile apps, web browsers, etc.). The LTR phase played the most direct role for meeting business requirements in the entire recommendation process (Zeng et al 2020). As high-click items may not always result in high transactions, trade-offs in C-TR and CVR were often required.…”