English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Predictive modeling is increasingly being employed to assist humandecision-makers. One purported advantage of replacing or augmenting humanjudgment with computer models in high stakes settings-- such as sentencing,hiring, policing, college admissions, and parole decisions-- is the perceived"neutrality" of computers. It is argued that because computer models do nothold personal prejudice, the predictions they produce will be equally free fromprejudice. There is growing recognition that employing algorithms does notremove the potential for bias, and can even amplify it if the training datawere generated by a process that is itself biased. In this paper, we provide aprobabilistic notion of algorithmic bias. We propose a method to eliminate biasfrom predictive models by removing all information regarding protectedvariables from the data to which the models will ultimately be trained. Unlikeprevious work in this area, our framework is general enough to accommodate dataon any measurement scale. Motivated by models currently in use in the criminaljustice system that inform decisions on pre-trial release and parole, we applyour proposed method to a dataset on the criminal histories of individuals atthe time of sentencing to produce "race-neutral" predictions of re-arrest. Inthe process, we demonstrate that a common approach to creating "race-neutral"models-- omitting race as a covariate-- still results in racially disparatepredictions. We then demonstrate that the application of our proposed method tothese data removes racial disparities from predictions with minimal impact onpredictive accuracy.

An algorithm for removing sensitive information: application to race-independent recidivism prediction