Abstract:
|
The purpose of this panel is to present recent developments of evidence-based policy making in light of machine learning and dynamic data visualizations. Case studies demonstrate how machine learning, interactive data visualizations and interdisciplinary approach may be effectively integrated to inform the process of policy making when it comes to people with disabilities and people with criminal history. Panelists will discuss research challenges, methodological approaches and findings relevant and useful to understanding the process of evidence building via data science and survey statistics. For example, machine learning-driven analysis of crime data linked across multiple data sources will shed light on correlates of crime, root causes of recidivism, life of people with criminal records and the effects of policy interventions. When it comes to people with disabilities, interactive linked data visualizations advanced by machine learning will identify correlates of disabilities at person-, neighborhood- and community levels, and guide policy interventions that may effectively support people with various types of disabilities.
|