Using Regression Kernels to Forecast A Failure to Appear in Court

By Richard A. Berk, Justin Bleich, Adam Kapelner, J. Henderson, G. Barnes, E. Kurtz. 2014

7 citations recorded by the source corpus.

Forecasts of prospective criminal behavior have long been an important feature of many criminal justice decisions. There is now substantial evidence that machine learning procedures will classify and forecast at least as well, and typically better, than logistic regression, which has to date dominated conventional practice. However, machine learning procedures are adaptive. They \learn" inductively from training data. As a result, they typically perform best with very large datasets. There is a need, therefore, for forecasting procedures with the promise of machine learning that will perform well with small to moderately-sized datasets. Kernel methods provide precisely that promise. In this paper, we oer an overview of kernel methods in regression settings and compare such a method, regularized with principle components, to stepwise logistic regression. We apply both to a timely and important criminal justice concern: a failure to appear (FTA) at court proceedings following an arraignment. A forecast of an FTA can be an important factor is a judge’s decision to release a defendant while awaiting trial and can inuence the conditions imposed on that release. Forecasting accuracy matters, and our kernel approach forecasts far more accurately than stepwise logistic regression. The methods developed here are implemented in the R package kernReg currently available on CRAN.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Cynthia Rudin
2. Berk Ustun
3. Jiaming Zeng
4. Tong Wang
5. Lesia Semenova
6. Chudi Zhong
7. Zhi Chen
8. Marco F. Huber

In Statistics and Probability

1. Cynthia Rudin
2. Berk Ustun
3. Jiaming Zeng
4. Nadia Burkart
5. Marco F. Huber
6. Tong Wang
7. Been Kim
8. Lesia Semenova

Citations in the corpus

• Interpretable classification models for recidivism prediction (2015, methodology): “Our design differs from split-sample designs where a substantial portion of the data is reserved for used as a test set (see, e.g., Tollenaar and van der Heijden 2013, Berk et al. 2014).”
• Nber Working Paper Series Human Decisions and Machine Predictions Human Decisions and Machine Predictions (2017, unknown): “For example Richard Berk and his colleagues have shown risk to be predictable in diverse criminal justice contexts; see for example the summary in Berk (2012) and subsequent results in Berk and Bleich (2013) and Berk et al. (2014).”