Dataiku > Case Studies > Coyote: From Churn Analysis to Predictive Safety

Coyote: From Churn Analysis to Predictive Safety

Customer Company Size

Large Corporate

Region

Europe

Country

France

Product

Coyote IoT-based devices
Coyote mobile applications
Dataiku

Tech Stack

IoT
Machine Learning
Predictive Analytics
Dataiku

Implementation Scale

Enterprise-wide Deployment

Impact Metrics

Customer Satisfaction
Productivity Improvements

Technology Category

Analytics & Modeling - Predictive Analytics
Analytics & Modeling - Machine Learning

Applicable Industries

Automotive
Telecommunications

Applicable Functions

Logistics & Transportation
Sales & Marketing

Use Cases

Predictive Maintenance
Traffic Monitoring
Vehicle Telematics

Services

Data Science Services
System Integration

About The Customer

Coyote is the European leader in real-time road information. The company uses IoT-based devices and mobile applications that enable their users to warn other drivers of traffic hazards and conditions that are detected while driving. Through its connected devices, Coyote collects extensive data on the different uses of its community, such as mileage, time spent on the road, or the number of alerts issued by the community members. The company aims to improve road safety using IoT devices.

The Challenge

Coyote, a European leader in real-time road information, uses IoT-based devices and mobile applications to warn drivers of traffic hazards and conditions. The company collects extensive data on the different uses of its community, such as mileage, time spent on the road, or the number of alerts issued by the community members. Initially, Coyote started with predictive analytics for improving their customer retention. However, they wanted to leverage the value of their vast data sources and implement a data-driven strategy at the heart of their core products and services. They aimed to improve road safety using IoT devices.

The Solution

Coyote developed a project using Dataiku to leverage vast amounts of IoT-derived data to identify steep, potentially dangerous turns on car roads and develop a dynamic recommended speed limit model to prevent road accidents. The machine learning model facilitated the detection of speed limit anomalies and enabled Coyote to estimate the global quality and reliability of the displayed speed limit. The project involved identifying all S-curves in France and calculating their angle, developing a dynamic recommended speed limit model based on this data, building and releasing a database of dangerous road curves, and monitoring and service optimization. Dataiku provided the end-to-end solution for connecting to data, building the dynamic speed limit model, feature engineering, deployment of database, data visualization and visual AutoML, and model monitoring and optimization.

Operational Impact

Coyote was able to develop a dynamic recommended speed limit model to prevent road accidents.
The machine learning model facilitated the detection of speed limit anomalies and enabled Coyote to estimate the global quality and reliability of the displayed speed limit.
Coyote was able to build and release a database of dangerous road curves.
Dataiku's centralized and elastic environment, collaboration features, and focus on operationalization have allowed Coyote to significantly reduce the time needed for feature engineering.

Quantitative Benefit

Coyote's marketing campaigns saw an 11% increase in efficiency thanks to increased knowledge of the actual uses of the service.
Coyote was able to successfully deploy and continuously optimize their predictive maintenance products and services for delivering quality driver assistance and improving road safety.