A method intended to evaluate racial disparities in lending decisions can yield very different results depending on tiny changes in how it guesses applicants’ races, according to a new Cornell-led study.
Two Cornell Tech master’s students have developed a prototype for augmented reality headsets to help people who are deaf or hard of hearing navigate one-on-one conversations.
Citizen science databases can be inconsistent, but Cornell researchers have developed a deep learning model that effectively corrects for location biases, leading to more reliable predictions.
A study of 765 million downloads from streaming service Spotify reveals clear patterns in musical preferences based on geography, gender, time of day and other considerations.
Cristos Goodrow ’91, YouTube’s vice president of engineering, leads the team that helps viewers sort through the millions of videos uploaded every day to find content they want to see.
On secondhand marketplaces like eBay, people trust online sellers who post their own high-quality photos of items for sale more than they trust those who use stock images or poor-quality photos, a Cornell Tech study has found.
Cornell Tech researchers developed a tool that causes smartphones to vibrate when users exceed time limits on certain apps, reducing usage of the apps by 20 percent and helping people tackle digital addiction.