"The problem of homelessness has become particularly acute in New York City. In 2010, an estimated 110,000 people slept in municipal shelters. Roughly a third of the people in these shelters have experienced a recent eviction, but it is difficult to predict which eviction notices will result in a homeless family. Predictive analytics may be able to help. In a joint project with the SumAll Foundation, the city Department of Homeless Services is analyzing data from all shelter check-ins, which include a family's most recent address. Visualizations are then created to potentially identify eviction “hotspots,” where the city needs to focus its mitigation. “Programs like this will help us show we are using our resources in the absolute best way possible to help the people that need them,” Sara Zuiderveen, the assistant commissioner of prevention services at DHS, told website Fast Co-Exist. "