Funded by the National Science Foundation (NSF), Penn State University, PARC and CMU are collaborating to develop a system to match service providers and receivers in real-time, based on both personal profile and dynamic context.
The first step in this effort was a previous NSF project in which Penn State and PARC collaborated to develop an app for timebanking. The app currently works with hOurworld’s Time and Talents system and we are releasing it in early June for an evaluation by members of the hOurworld timebank network.
The second step, also funded by NSF and currently underway, is to build on the existing app to develop a transaction partner recommender system, which will suggest people who are best suited to respond to your offer or request. The recommendations are based on their profile, their location and predicted travel patterns and their availability. This means that if you ask someone to pick up some eggs from the supermarket for you, someone at the supermarket who travels home past your house will have the request recommended to her. We are currently working on a prototype and expect to begin an experimental trial of the prototype in the summer.