Interpretable classification models for recidivism prediction

We investigate a long-debated question, which is how to create predictive models of recidivism that are sufficiently accurate, transparent and interpretable to use for decision making. This question is complicated as these models are used to support different decisions, from sentencing, to determini...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of the Royal Statistical Society. Series A, Statistics in society Ročník 180; číslo 3; s. 689 - 722
Hlavní autori: Zeng, Jiaming, Ustun, Berk, Rudin, Cynthia
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: John Wiley & Sons Ltd 01.06.2017
Predmet:
Binary classification
Interpretability
Machine learning
Recidivism
Scoring systems
ISSN:0964-1998, 1467-985X
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We investigate a long-debated question, which is how to create predictive models of recidivism that are sufficiently accurate, transparent and interpretable to use for decision making. This question is complicated as these models are used to support different decisions, from sentencing, to determining release on probation to allocating preventative social services. Each case might have an objective other than classification accuracy, such as a desired true positive rate TPR or false positive rate FPR. Each (TPR, FPR) pair is a point on the receiver operator characteristic (ROC) curve. We use popular machine learning methods to create models along the full ROC curve on a wide range of recidivism prediction problems. We show that many methods (support vector machines, stochastic gradient boosting and ridge regression) produce equally accurate models along the full ROC curve. However, methods that are designed for interpretability (classification and regression trees and C5.0) cannot be tuned to produce models that are accurate and/or interpretable. To handle this shortcoming, we use a recent method called supersparse linear integer models to produce accurate, transparent and interprétable scoring systems along the full ROC curve. These scoring systems can be used for decision making for many different use cases, since they are just as accurate as the most powerful black box machine learning models for many applications, but completely transparent, and highly interpretable.
ISSN:0964-1998
1467-985X
DOI:10.1111/rssa.12227