JavaScript is disabled in your browser.
Please enable JavaScript settings in your browser to allow this website work correctly.
  • Java


Bike sharing systems are a means of renting bicycles where the process of obtaining membership, rental, and bike return is automated via a network of kiosk locations throughout a city. The data generated by these systems covers the duration of travel, departure location, arrival location, and time elapsed is explicitly recorded. We used machine learning to predict the demand for bikes based on historical usage patterns and weather data.

Two models were used, based on Stochastic Gradient Descent with L2 regulation and based on RandomForest. Then we assessed mean absolute error and the second model performed better.

How can we help you?