Knowledge-Based Systems ( IF 8.8 ) Pub Date : 2020-11-25 , DOI: 10.1016/j.knosys.2020.106629 F. Ortega , J. Mayor , D. López-Fernández , R. Lara-Cabrera
CF4J 2.0 is a framework for conducting research experiments based on collaborative filtering. This framework has been designed keeping the scientific community in mind. It includes major features such as a high number of implemented algorithms from the state-of-the-art, several quality measures and parallel execution of the techniques, as well as abstract classes and interfaces to allow developers to extend and customize the library. Furthermore, this new version of the library focuses on the following key features: simple deployment of collaborative filtering experiments, reproducible science, hyper-parameter optimization, data analysis, and openness to the community as an open-source project.
中文翻译:
CF4J 2.0:使Java的协作过滤适应基于协作过滤的推荐系统的新挑战
CF4J 2.0是用于基于协作过滤进行研究实验的框架。设计此框架时要牢记科学界。它包括主要功能,例如大量来自最新技术的已实现算法,若干质量度量和技术的并行执行,以及允许开发人员扩展和自定义库的抽象类和接口。此外,该库的新版本重点关注以下关键功能:协作过滤实验的简单部署,可重复的科学,超参数优化,数据分析以及作为开放源代码项目向社区开放。