Recommender Systems (RS) support users to find relevant contents, such as movies, books, songs, and other products based on their preferences. Such preferences are gathered by analyzing past users’ interactions, however, data collected for this purpose are typically prone to sparsity and high dimensionality. Clustering-based techniques have been proposed to handle those problems effectively and efficiently by segmenting the data into a number of similar groups based on predefined characteristics. Although such techniques have gained increasing attention in the recommender systems community, they are usually bound to a particular recommender system and/or require critical parameters, such as the number of clusters. In this paper, we present three variants of a general-purpose method to optimally extract users’ groups from a hierarchical clustering algorithm, specifically targeting RS problems. The proposed extraction methods do not require critical parameters and enable any recommender algorithm to be used at the recommendation step. Our experiments have shown promising recommendation results in the context of nine well-known public datasets from different domains.

推荐系统（RS）支持用户根据自己的喜好查找相关内容，例如电影，书籍，歌曲和其他产品。通过分析过去的用户交互来收集此类首选项，但是，为此目的收集的数据通常容易出现稀疏和高维度。已经提出了基于聚类的技术，以通过基于预定义的特征将数据划分为多个相似的组来有效地解决这些问题。尽管这样的技术在推荐器系统社区中已得到越来越多的关注，但它们通常绑定到特定的推荐器系统和/或需要关键参数，例如群集数。在本文中，我们提出了三种通用方法的变体，可以从分层聚类算法中最佳地提取用户组，尤其是针对RS问题。提出的提取方法不需要关键参数，并且可以在推荐步骤使用任何推荐算法。我们的实验在来自不同领域的九个知名公共数据集的背景下显示出令人鼓舞的推荐结果。