Daisy Intelligence Hackathon Solution 2022
bicyc-L uses a predictive Machine Learning model to rate the City of Toronto’s bike racks as ‘safe’ or ‘unsafe’, to provide riders with guidance on secure parking locations
The Toronto Police Service Bike Theft and Toronto’s Outdoor High-Capacity Bike Parking datasets were combined.
Numpy, Pandas, and Regex were used for data manipulation. Knime was used to create and train the model.
bicyc-L uses a generalized linear regression model due to its simplicity and accuracy.
The user interface was modelled in Figma. You can access the prototype here: https://www.figma.com/proto/crifEUACzZE6Dnl3Ye1OWs/BicycL?node-id=2%3A52&scaling=scale-down&page-id=0%3A1&starting-point-node-id=2%3A2
- Fewer theft incidents
- Fewer police resources used
- Fewer worries for riders
- More security for riders
- More savings $
- Expanded cities and towns (outside Toronto)
- Complete the front end
- Location-based reccomendations