arXiv subjects

Kuan Zou

Publications and source records attributed to Kuan Zou.

3 recordsLinked to original sources

arXiv2025

A Survey of Real-World Recommender Systems: Challenges, Constraints, and Industrial Perspectives

Recommender systems have generated tremendous value for both users and businesses, drawing significant attention from academia and industry alike. However, due to practical constraints, academic research remains largely confined to offline dataset optimizations, lacking access to real user data and large-scale recommendation platforms. This limitation reduces practical relevance, slows technological progress, and hampers a full understanding of the key challenges in recommender systems. In this survey, we provide a systematic review of industrial recommender systems and contrast them with their academic counterparts. We highlight key differences in data scale, real-time requirements, and evaluation methodologies, and we summarize major real-world recommendation scenarios along with their associated challenges. We then examine how industry practitioners address these challenges in Transaction-Oriented Recommender Systems and Content-Oriented Recommender Systems, a new classification grounded in item characteristics and recommendation objectives. Finally, we outline promising research directions, including the often-overlooked role of user decision-making, the integration of economic and psychological theories, and concrete suggestions for advancing academic research. Our goal is to enhance academia's understanding of practical recommender systems, bridge the growing development gap, and foster stronger collaboration between industry and academia.

cs.IR↗

arXiv2024

Hesitation and Tolerance in Recommender Systems

Users' interactions with recommender systems often involve more than simple acceptance or rejection. We highlight two overlooked states: hesitation, when people deliberate without certainty, and tolerance, when this hesitation escalates into unwanted engagement before ending in disinterest. Across two large-scale surveys (N=6,644 and N=3,864), hesitation was nearly universal, and tolerance emerged as a recurring source of wasted time, frustration, and diminished trust. Analyses of e-commerce and short-video platforms confirm that tolerance behaviors, such as clicking without purchase or shallow viewing, correlate with decreased activity. Finally, an online field study at scale shows that even lightweight strategies treating tolerance as distinct from interest can improve retention while reducing wasted effort. By surfacing hesitation and tolerance as consequential states, this work reframes how recommender systems should interpret feedback, moving beyond clicks and dwell time toward designs that respect user value, reduce hidden costs, and sustain engagement.

cs.IR↗

arXiv2022

Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval

Passage retrieval is a fundamental task in information retrieval (IR) research, which has drawn much attention recently. In the English field, the availability of large-scale annotated dataset (e.g, MS MARCO) and the emergence of deep pre-trained language models (e.g, BERT) has resulted in a substantial improvement of existing passage retrieval systems. However, in the Chinese field, especially for specific domains, passage retrieval systems are still immature due to quality-annotated dataset being limited by scale. Therefore, in this paper, we present a novel multi-domain Chinese dataset for passage retrieval (Multi-CPR). The dataset is collected from three different domains, including E-commerce, Entertainment video and Medical. Each dataset contains millions of passages and a certain amount of human annotated query-passage related pairs. We implement various representative passage retrieval methods as baselines. We find that the performance of retrieval models trained on dataset from general domain will inevitably decrease on specific domain. Nevertheless, a passage retrieval system built on in-domain annotated dataset can achieve significant improvement, which indeed demonstrates the necessity of domain labeled data for further optimization. We hope the release of the Multi-CPR dataset could benchmark Chinese passage retrieval task in specific domain and also make advances for future studies.

cs.IR↗