
Assessing regulatory fairness through machine learning
Research News Release
EurekAlert! provides eligible reporters with free access to embargoed and breaking news releases.
Eligibility GuidelinesEurekAlert! offers eligible public information officers paid access to a reliable news release distribution service.
Eligibility GuidelinesEurekAlert! is a service of the American Association for the Advancement of Science.
Applying machine learning to a U.S. Environmental Protection Agency initiative, Stanford researchers reveal how key design elements determine what communities bear the burden of pollution. The approach could help ensure fairness and accountability in machine learning used by government regulators.
It's a common assumption among marketers that if you can customize any form of marketing, particularly mobile advertising, you'll get better results. With this in mind, mobile marketing relies significantly on user tracking data as a cornerstone advertising strategy.
Researchers from the IXA group at the UPV/EHU are collaborating with Osakidetza (the Basque Regional Health Service) to create a system for automatically extracting adverse drug reactions from electronic health records written in Spanish. The researchers have conducted different tests using both machine learning and deep learning, with the aim of building a robust model for extracting relations between drug-disease pairs based on clinical text mining.
Dr. Jianqing Chen and Dr. Srinivasan Raghunathan of The University of Texas at Dallas examined the role and economic impacts of recommender systems, and how they affect consumers' decisions.
Over the next month, 209 U.S. counties in the United States will need to implement crisis workforce strategies to deal with potentially dangerous shortfalls of intensive care unit doctors, according to a new analysis published today. The analysis draws on data from a just launched county-level hospital workforce estimator, one that takes into account the strain on staffing due to the COVID-19 pandemic.
A group of researchers, spanning six universities and three continents, are sounding the alarm on a topic not often discussed in the context of conservation--misinformation. In a recent study published in FACETS, the team, including Dr. Adam Ford, Canada Research Chair in Wildlife Restoration Ecology, and Dr. Clayton Lamb, Liber Ero Fellow, explain how the actions of some scientists, advocacy groups and the public are eroding efforts to conserve biodiversity.
In "Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images," researchers at the NYU Tandon School of Engineering led by Siddharth Garg, professor of electrical and computer engineering, explored whether private data could still be recovered from images that had been "sanitized" by such deep-learning discriminators as privacy protecting GANs (PP-GANs).
Wildlife tourism including white shark cage-diving is growing in popularity, but these industries remain highly contentious amongst tourists, conservationists, and scientists alike. To help solve this question of 'is wildlife tourism good or bad?', a tool to help managers assess these industries has been created by scientists from Flinders University, the Georgia Aquarium and colleagues.
Researchers examined e-scooter use in Washington, D.C. and found that built environment and demographics both matter. Tourist attractions, hotels and metro stops are all predictive of higher destinations. Scooter traffic is almost all in the downtown area, near the Mall, the White House and Congress. Younger median age, percentage of bachelor's degrees and population density each were positive predictors for both trip origins and destinations. This model will help transportation planners figure out what drives e-scooter use.
CATONSVILLE, MD, February 25, 2021 - Short notice versus no advance notice makes a huge difference when it comes to employee scheduling in the restaurant industry. New research in the INFORMS journal Management Science finds checks for parties handled by servers who were asked (with no advance notice) to stay longer than their scheduled shift dropped by 4.4%, on average.