With the meteoric rise of video-on-demand (VOD) platforms, users face the challenge of sifting through an expansive sea of content to uncover shows that closely match their preferences. To address this information overload dilemma, VOD services have increasingly incorporated recommender systems powered by algorithms that analyze user behavior and suggest personalized content. However, a majority of existing recommender systems depend on explicit user feedback in the form of ratings and reviews, which can be difficult and time-consuming to collect at scale. This presents a key research gap, as leveraging users' implicit feedback patterns could provide an alternative avenue for building effective video recommendation models, circumventing the need for explicit ratings. However, prior literature lacks sufficient exploration into implicit feedback-based recommender systems, especially in the context of modeling video viewing behavior. Therefore, this paper aims to bridge this research gap by proposing a novel video recommendation technique that relies solely on users' implicit feedback in the form of their content viewing percentages.

翻译：随着视频点播（VOD）平台的迅猛发展，用户面临在海量内容中筛选出符合个人偏好的节目这一挑战。为解决这一信息过载困境，VOD服务日益引入由算法驱动的推荐系统，通过分析用户行为来推送个性化内容。然而，现有推荐系统大多依赖用户以评分及评论形式提供的显式反馈，这类数据在大规模场景下收集起来既困难又耗时。这构成了一个关键的研究空白，因为利用用户的隐式反馈模式或可成为构建高效视频推荐模型的另一途径，从而规避对显式评分的依赖。然而，现有文献中对基于隐式反馈的推荐系统研究尚不充分，尤其是在建模视频观看行为方面。因此，本文旨在填补这一研究空白，提出一种仅依赖用户内容观看百分比这一隐式反馈的新型视频推荐技术。