An Agent-Based Modeling Approach To Addressing The Opioid Crisis
With Agent-Based Modeling (ABM), we can predict outcomes for local communities of pain patients. This is an exciting proof of concept suggesting that an ABM approach can successfully model unique community-level health outcomes. An ABM tailored to the Durham, NC pain patient community suggests that increased naloxone availability and decreased emergency department dosages are associated with improved outcomes. Our findings also suggest that interventions such as increased buprenorphine availability and decreased prescribing rates do not meaningful affect outcomes. This is evidence that recent policies may not have their intended effect.
An Examination Of Bias In Criminal Risk-Assessment
Over the last few years, algorithic decision-making has grown rapidly across all domains. It's hard to imagine a domain more high-stakes than the criminal justice system where a decisions have lifelong consequences. Unfortunately, research has shown that these algorithms can be biased in their decision-making, specifically on the basis of race. There are three primary issues associated with reducing bias in criminal justice algorithms; 1) identifying, 2) quantifying, 3) and remedying bias. These problems call for transparency, establishment of clear criterion, and constant evaluation. With this process, public officials can proactively and consistently consider bias in any criminal justice algorithm.
The Influence Of Transportation Accessibility On Property Value
In dense cities like New York City, transportation availability is considered an ever-important factor in selecting a place to live. How influential is transportation accessibility in real estate value? To answer this question, we explore the effects of transportation access on housing sale prices in NYC using subway, bike share, taxi and Uber data.
Detecting Solar Panels From Satellite Imagery
As consumer solar panel adoption increases, so does interest in solar consumption habits. Policymakers are reliant on accurate measures of the saturation of solar panels to inform structuring of tax incentive programs. Traditional consumer surveys are costly and time-consuming to collect, and ultimately can often only give a partial view of the market. Satellite imagery, on the other hand, provides unbiased overhead views of households all over the country. The use of convolutional neural networks and satellite imagery for solar panel detection may result in more consistent and cost-effective assessment of solar adoption.
