Dataiku Case Studies Smart Cities: Enhancing Public Services with DSS

Edit This Case Study Record

	Smart Cities: Enhancing Public Services with DSS Dataiku

Smart Cities: Enhancing Public Services with DSS

Dataiku

Technology Category	Analytics & Modeling - Predictive Analytics Application Infrastructure & Middleware - Data Exchange & Integration
Applicable Industries	Cities & Municipalities Transportation
Applicable Functions	Logistics & Transportation
Use Cases	Predictive Replenishment Smart City Operations
Services	Data Science Services Software Design & Engineering Services
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. Read More
About 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. Read More
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. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Predictive Analytics

Application Infrastructure & Middleware - Data Exchange & Integration

Applicable Industries

Cities & Municipalities

Transportation

Applicable Functions

Logistics & Transportation

Use Cases

Predictive Replenishment

Smart City Operations

Services

Data Science Services

Software Design & Engineering Services

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.

About 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.

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.

Impact #1	Parkeon was able to develop the 'Path to Park' app with DSS, which is a simple and intuitive example of a modern data product.
Impact #2	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.
Impact #3	Parkeon can use their data to develop and refine predictive models that put drivers in the right place at the right time.

Impact #1

Parkeon was able to develop the 'Path to Park' app with DSS, which is a simple and intuitive example of a modern data product.

Impact #2

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.

Impact #3

Parkeon can use their data to develop and refine predictive models that put drivers in the right place at the right time.

Benefit #1	The app predicts 3 parking options around the driver’s location.
Benefit #2	There is more than an 80% probability for drivers to find a parking spot in the near vicinity.
Benefit #3	The app allows for fast iteration enabling tests & improvements of the predictive algorithm.

Benefit #1

The app predicts 3 parking options around the driver’s location.

Benefit #2

There is more than an 80% probability for drivers to find a parking spot in the near vicinity.

Benefit #3

The app allows for fast iteration enabling tests & improvements of the predictive algorithm.

Download PDF Version

Overview

Smart Cities: Enhancing Public Services with DSS

Operational Impact

Quantitative Benefit