Abstract
Risk scores are simple classification models that let users quickly assess risk by adding, subtracting, and multiplying a few small numbers. Such models are widely used in healthcare and criminal justice, but are often built ad hoc. In this paper, we present a principled approach to learn risk scores that are fully optimized for feature selection, integer coefficients, and operational constraints. We formulate the risk score problem as a mixed integer nonlinear program, and present a new cutting plane algorithm to efficiently recover its optimal solution. Our approach can fit optimized risk scores in a way that scales linearly with the sample size of a dataset, provides a proof of optimality, and obeys complex constraints without parameter tuning. We illustrate these benefits through an extensive set of numerical experiments, and an application where we build a customized risk score for ICU seizure prediction.
Keywords
Integer (computer science)Set (abstract data type)Computer scienceCutting-plane methodSelection (genetic algorithm)Feature (linguistics)Simple (philosophy)Mathematical optimizationArtificial intelligenceInteger programmingAlgorithmMathematics
Affiliated Institutions
Related Publications
Least angle regression
The purpose of model selection algorithms such as All Subsets, Forward Selection and Backward Elimination is to choose a linear model on the basis of the same set of data to whi...
Feature Selection via Mathematical Programming
The problem of discriminating between two finite point sets in n-dimensional feature space by a separating plane that utilizes as few of the features as possible is formulated a...
Feature selection for high-dimensional genomic microarray data
We report on the successful application of feature selection methods to a classification problem in molecular biology involving only 72 data points in a 7130 dimensional space. ...
Covariance selection for nonchordal graphs via chordal embedding
We describe algorithms for maximum likelihood estimation of Gaussian graphical models with conditional independence constraints. This problem is also known as covariance selecti...
A learner-independent evaluation of the usefulness of statistical phrases for automated text categorization
In this work we investigate the usefulness of n-grams for document indexing in text categorization (TCi We call-gram a set g k of n word stems, and we say that g k occurs in a d...
Publication Info
- Year
- 2017
- Type
- article
- Pages
- 1125-1134
- Citations
- 48
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
48
OpenAlex
Cite This
Berk Ustun,
Cynthia Rudin
(2017).
Optimized Risk Scores.
, 1125-1134.
https://doi.org/10.1145/3097983.3098161
Identifiers
- DOI
- 10.1145/3097983.3098161