AI Case Study
Parkeon predicts vehicle parking space availability using machine learning and predictive algorithms from Dataiku
Parkeon, which supplies parking and transit systems to customers around the globe, used Dataiku DSS to perform transport data analytics and build an app which can predict parking space availability. This is done using data from its parking meters and machine learning.
"Using Data Science Studio, Parkeon built a mobile application that predicts zones where drivers are more likely to find parking. Despite a simple interface, the app uses state-of-the-art predictive algorithms. The technology uses millions of transactions coming from parking meters every day and combines them with geographical data coming from the open source OpenStreetMap (e.g. points of interest like restaurants and shops).
* Streets are divided into segments and enriched with varying information such as the surrounding points of interest
* Data coming from the parking meters are cross-checked with street segments and points of interest."
Parkeon claims that it can "predict parking availability in each street according to parking meter data and points of interest data".
"Dataiku Data Science Studio (DSS) is a powerful predictive analytics solution that allows users to connect to a wide variety of data, quickly clean that data (in the GUI or with code), and enables them to creatively factor-in datasets to create predictive models. These models can be configured and tweaked, as needed, in order to visualize your own unique business scenarios. The analytics process uses a rich machine learning interface to empower your company to build predictive services based on past and incoming data."
"Parkeon supplies parking and transit systems to customers around the globe. Their core expertise is payment solutions such as multi-space parking meters, mobile phone payments, ticket vending machines, and more. Parkeon has access to considerable volumes of data regarding the habits of city drivers. Parkeon wanted a solution that could help them:
* Build an app with reliable predictions of parking availability
* Enrich the parking meter data to create greater intelligence."
Geographic data from OpenStreetMap, parking meter data