The Case for Temporal Transparency: Detecting Policy Change Events in Black-Box Decision Making Systems
This addresses transparency issues in black-box systems for stakeholders like regulators or affected individuals, but it is incremental as it builds on existing changepoint detection methods.
The paper tackles the problem of detecting policy changes in black-box decision making systems by introducing temporal transparency, which maps to changepoint detection methods, and successfully identifies both announced and unannounced changes in experiments on the New York Stop-question-and-frisk dataset.
Bringing transparency to black-box decision making systems (DMS) has been a topic of increasing research interest in recent years. Traditional active and passive approaches to make these systems transparent are often limited by scalability and/or feasibility issues. In this paper, we propose a new notion of black-box DMS transparency, named, temporal transparency, whose goal is to detect if/when the DMS policy changes over time, and is mostly invariant to the drawbacks of traditional approaches. We map our notion of temporal transparency to time series changepoint detection methods, and develop a framework to detect policy changes in real-world DMS's. Experiments on New York Stop-question-and-frisk dataset reveal a number of publicly announced and unannounced policy changes, highlighting the utility of our framework.