Dataiku > Case Studies > Smart Cities: Enhancing Public Services with DSS

Smart Cities: Enhancing Public Services with DSS

Dataiku Logo
Customer Company Size
Large Corporate
Country
  • Worldwide
Product
  • Path to Park
Tech Stack
  • Data Science Studio
  • OpenStreetMap
  • iOS app
Implementation Scale
  • Enterprise-wide Deployment
Impact Metrics
  • Productivity Improvements
  • Customer Satisfaction
Technology Category
  • Analytics & Modeling - Predictive Analytics
  • Application Infrastructure & Middleware - Data Exchange & Integration
Applicable Industries
  • Cities & Municipalities
  • Transportation
Applicable Functions
  • Logistics & Transportation
Use Cases
  • Smart City Operations
  • Predictive Replenishment
Services
  • Data Science Services
  • Software Design & Engineering Services
About The Customer
Parkeon is a global supplier of parking and transit systems. Their core expertise lies in payment solutions such as multi-space parking meters, mobile phone payments, ticket vending machines, and more. Parkeon systems are found in over 3,500 cities and 55 countries worldwide. They have access to considerable volumes of data regarding the habits of city drivers and wanted to leverage this data to build an app with reliable predictions of parking availability and enrich the parking meter data to create greater intelligence.
The Challenge
Parkeon, a global supplier of parking and transit systems, wanted to leverage the vast volumes of data they had access to regarding city drivers' habits. They aimed to design a powerful parking availability prediction B2C application that could provide reliable predictions of parking availability and enrich the parking meter data to create greater intelligence. The challenge was to turn the parking meter data and geolocalized data into accurate predictions that could be used in a user-friendly mobile application.
The Solution
Parkeon used Data Science Studio to build a mobile application, 'Path to Park', that predicts zones where drivers are more likely to find parking. The application uses state-of-the-art predictive algorithms to analyze millions of transactions from parking meters every day and combines them with geographical data from the open-source OpenStreetMap. Streets are divided into segments and enriched with varying information such as the surrounding points of interest. The data from the parking meters are cross-checked with street segments and points of interest to provide accurate parking availability predictions.
Operational Impact
  • Parkeon was able to develop the 'Path to Park' app with DSS, which is a simple and intuitive example of a modern data product.
  • The predictive algorithm developed with DSS is embedded into the app, allowing Parkeon to predict parking availability in each street according to parking meter data and points of interest data.
  • Parkeon can use their data to develop and refine predictive models that put drivers in the right place at the right time.
  • The app can scale with its growth thanks to machine learning and hybrid architecture.
Quantitative Benefit
  • The app predicts 3 parking options around the driver’s location.
  • There is more than an 80% probability for drivers to find a parking spot in the near vicinity.
  • The app allows for fast iteration enabling tests & improvements of the predictive algorithm.
  • The app has easy scalability to extend the product to several cities.

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

Related Case Studies.

Contact us

Let's talk!
* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.