Recommender Systems have become a very useful tool for a large variety of domains. Researchers have been attempting to improve their algorithms in order to issue better predictions to the users. However, one of the current challenges in the area refers to how to properly evaluate the predictions generated by a recommender system. In the extent of offline evaluations, some traditional concepts of evaluation have been explored, such as accuracy, Root Mean Square Error and P@N for top-k recommendations. In recent years, more research have proposed some new concepts such as novelty, diversity and serendipity. These concepts have been addressed with the goal to satisfy the users' requirements. Numerous definitions and metrics have been proposed in previous work. On the absence of a specific summarization on evaluations of recommendation combining traditional metrics and recent progresses, this paper surveys and organizes the main research that present definitions about concepts and propose metrics or strategies to evaluate recommendations. In addition, this survey also settles the relationship between the concepts, categorizes them according to their objectives and suggests potential future topics on user satisfaction.
Description
How good your recommender system is? A survey on evaluations in recommendation | International Journal of Machine Learning and Cybernetics
%0 Journal Article
%1 silveira2019recommender
%A Silveira, Thiago
%A Zhang, Min
%A Lin, Xiao
%A Liu, Yiqun
%A Ma, Shaoping
%D 2019
%J International Journal of Machine Learning and Cybernetics
%K diversity evaluation novelty recommender seredipity utility
%N 5
%P 813--831
%R 10.1007/s13042-017-0762-9
%T How good your recommender system is? A survey on evaluations in recommendation
%U https://doi.org/10.1007/s13042-017-0762-9
%V 10
%X Recommender Systems have become a very useful tool for a large variety of domains. Researchers have been attempting to improve their algorithms in order to issue better predictions to the users. However, one of the current challenges in the area refers to how to properly evaluate the predictions generated by a recommender system. In the extent of offline evaluations, some traditional concepts of evaluation have been explored, such as accuracy, Root Mean Square Error and P@N for top-k recommendations. In recent years, more research have proposed some new concepts such as novelty, diversity and serendipity. These concepts have been addressed with the goal to satisfy the users' requirements. Numerous definitions and metrics have been proposed in previous work. On the absence of a specific summarization on evaluations of recommendation combining traditional metrics and recent progresses, this paper surveys and organizes the main research that present definitions about concepts and propose metrics or strategies to evaluate recommendations. In addition, this survey also settles the relationship between the concepts, categorizes them according to their objectives and suggests potential future topics on user satisfaction.
@article{silveira2019recommender,
abstract = {Recommender Systems have become a very useful tool for a large variety of domains. Researchers have been attempting to improve their algorithms in order to issue better predictions to the users. However, one of the current challenges in the area refers to how to properly evaluate the predictions generated by a recommender system. In the extent of offline evaluations, some traditional concepts of evaluation have been explored, such as accuracy, Root Mean Square Error and P@N for top-k recommendations. In recent years, more research have proposed some new concepts such as novelty, diversity and serendipity. These concepts have been addressed with the goal to satisfy the users' requirements. Numerous definitions and metrics have been proposed in previous work. On the absence of a specific summarization on evaluations of recommendation combining traditional metrics and recent progresses, this paper surveys and organizes the main research that present definitions about concepts and propose metrics or strategies to evaluate recommendations. In addition, this survey also settles the relationship between the concepts, categorizes them according to their objectives and suggests potential future topics on user satisfaction.},
added-at = {2023-09-10T16:42:53.000+0200},
author = {Silveira, Thiago and Zhang, Min and Lin, Xiao and Liu, Yiqun and Ma, Shaoping},
biburl = {https://www.bibsonomy.org/bibtex/23aa4d046a78e43e40ea0851ce8b92179/sdo},
day = 01,
description = {How good your recommender system is? A survey on evaluations in recommendation | International Journal of Machine Learning and Cybernetics},
doi = {10.1007/s13042-017-0762-9},
interhash = {b3c318a9c63deb6783906bc31002f788},
intrahash = {3aa4d046a78e43e40ea0851ce8b92179},
issn = {1868-808X},
journal = {International Journal of Machine Learning and Cybernetics},
keywords = {diversity evaluation novelty recommender seredipity utility},
month = may,
number = 5,
pages = {813--831},
timestamp = {2023-09-10T16:42:53.000+0200},
title = {How good your recommender system is? A survey on evaluations in recommendation},
url = {https://doi.org/10.1007/s13042-017-0762-9},
volume = 10,
year = 2019
}