what
This project—Shyft—was the result of a daylong IDEO Makeathon. About 60 of us were lucky enough to be selected to participate out of 550+ applicants. My amazing team of 5 from diverse backgrounds (mechanical engineering to UI design and interactive art) created a product that uses machine learning to help interior designers create better office spaces.
Our product, called Shyft, was designed to help with the layout of furniture in a space as well as the layout of people. We wanted to make sure we were designing to augment the power of designers, not replace them. Our process was to take a new office space and team specs and use historical data and machine learning to predict an efficient layout. We decided to measure efficiency based on both productivity (i.e. revenue, email patterns, etc.) and happiness (i.e. using survey metrics). The next step in the process was to attach sensors to furniture to collect data for a couple of weeks about how the furniture was being used and how it got moved around. This would then be fed back into the system to improve the layout. Our prototype included a test sensor that detected when someone was sitting in a chair.
team members
Kelly Wagman, Ray LC, Rachel Robbins, Yihan Zhou, Josh Brown
when
2018
