We wanted to explore uses for machine learning, so we decided to create a tool to predict availability of Capital Bikeshare stations depending on location, time of day, and weather.
We used the large amount of trip data DC's Capital Bikeshare has made available to the public, combined with other historical data, and applied statistical methods. To increase accuracy, we added weather data to the learning system.
We got a few RadBeacons to play around with, so we integrated them with Slack to create a "check-in" feature that alerts team members via Slack when someone gets into the office.
We created a prototype AR app for the iPhone that shows users where the nearest Capital Bikeshare station is relative to the user’s location and directional orientation. The AR overlay shows the name and distance of each station.