Capital Bikeshare

Machine learning

Products

Timeframe

5 weeks

Challenge

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.

Solution

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.

Blog Posts

Results

We quickly built a web page and a REST API that collects user input and displays predictions for the given location, date, and time. Next, we decided to add a conversational interface so we can access the API using natural language. We also added a Slack bot integration so that users can access the solution right in the chat window.

Our Latest Projects

Chatbots

Our interns explored creating a chatbot using IBM's Watson API to onboard new employees and answer their employment and HR-related questions.

Read Our Lab Notes

Internal Alexa Skills

We created an Alexa skill that integrates with our beacon- and Slack-enabled Mission Data Office app. Staffers can ask the Amazon Echo to identify the specific location of someone in the office. We also created a skill for Alexa to tell our DC staffers which food trucks are outside the office at any given time.

Read Our Lab Notes
No results match this filter.

We use cookies to deliver the best possible experience on our website. To learn more, visit our privacy policy. By continuing to use this site, you consent to our use of cookies.

Accept