Corpus ID: 32545283

It's Time to Consider "Time" when Evaluating Recommender-System Algorithms [Proposal]

@article{Beel2017ItsTT,
  title={It's Time to Consider "Time" when Evaluating Recommender-System Algorithms [Proposal]},
  author={J. Beel},
  journal={ArXiv},
  year={2017},
  volume={abs/1708.08447}
}
  • J. Beel
  • Published 2017
  • Computer Science
  • ArXiv
In this position paper, we question the current practice of calculating evaluation metrics for recommender systems as single numbers (e.g. precision p=.28 or mean absolute error MAE = 1.21). We argue that single numbers express only average effectiveness over a usually rather long period (e.g. a year or even longer), which provides only a vague and static view of the data. We propose that recommender-system researchers should instead calculate metrics for time-series such as weeks or months… Expand

References

SHOWING 1-10 OF 139 REFERENCES
Towards reproducibility in recommender-systems research
Evaluating collaborative filtering over time
Déjà Vu: The Importance of Time and Causality in Recommender Systems
A Survey of Accuracy Evaluation Metrics of Recommendation Tasks
Algorithms Aside: Recommendation As The Lens Of Life
Introduction to the Special Issue on Recommender System Benchmarking
The Architecture and Datasets of Docear's Research Paper Recommender System
...
1
2
3
4
5
...