Supersparse Linear Integer Models for Predictive Scoring Systems
Machine Learning
2013-06-26 v1
Abstract
We introduce Supersparse Linear Integer Models (SLIM) as a tool to create scoring systems for binary classification. We derive theoretical bounds on the true risk of SLIM scoring systems, and present experimental results to show that SLIM scoring systems are accurate, sparse, and interpretable classification models.
Cite
@article{arxiv.1306.5860,
title = {Supersparse Linear Integer Models for Predictive Scoring Systems},
author = {Berk Ustun and Stefano Traca and Cynthia Rudin},
journal= {arXiv preprint arXiv:1306.5860},
year = {2013}
}
Comments
Short version