Dataiku > Case Studies > Ensuring Subscriber Retention and Loyalty

Ensuring Subscriber Retention and Loyalty

Dataiku Logo
Customer Company Size
Mid-size Company
Region
  • Europe
Country
  • France
Product
  • Dataiku Data Science Studio (DSS)
Tech Stack
  • Machine Learning
  • Predictive Behavioral Analysis
Implementation Scale
  • Enterprise-wide Deployment
Impact Metrics
  • Customer Satisfaction
  • Brand Awareness
Technology Category
  • Analytics & Modeling - Predictive Analytics
Applicable Industries
  • Telecommunications
Applicable Functions
  • Sales & Marketing
Use Cases
  • Predictive Replenishment
Services
  • Data Science Services
About The Customer
Coyote is a French company that provides real-time road information. The company was established in 2005 and has grown to have 200 employees. In 2014, Coyote generated a turnover of over € 100 million and currently has 4.8 million users across Europe. The Coyote devices allow users to interconnect to the entire community in order to warn other drivers of the different traffic hazards and traffic conditions (traffic obstruction, accident, radar, etc.) detected during their rides.
The Challenge
Coyote, a French leader in real-time road information, was facing a challenge in retaining its customer base and enhancing its service quality. The company wanted to optimize its loyalty program to encourage customers to increase device use. To achieve this, Coyote needed a technical solution that would enable them to segment its customer base by user profile, qualify incoming data, and quantify device use through anonymous data analysis. The company understood that the more data it collected, the better its service would be. Therefore, improving retention rates was crucial to enhance the service quality and acquire more users.
The Solution
Coyote decided to use Dataiku's Data Science Studio (DSS) to build and implement a predictive behavioral analysis application to segment customers. The application automatically compiled and processed heterogeneous and completely anonymized data, including contractual data, customer declared data, and real-time device data. This data was then processed by a machine-learning algorithm to model user behavior. The model and its results were subsequently adjusted to optimize marketing campaigns. With this score, Coyote was able to segment its user base with very high accuracy, leading to significant optimization of marketing campaigns.
Operational Impact
  • Increase in the performance of outbound call campaigns by 11%
  • Adaptation of marketing campaigns due to increased knowledge of the actual uses of the service
  • Significant improvement in data management
Quantitative Benefit
  • Efficiency of outbound call campaigns increased by 11%
  • Significant improvement in data management leading to more effective marketing campaigns
  • Increased knowledge of actual service uses leading to more targeted marketing campaigns

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.