In today’s data-driven economy, understanding customer behavior is key for personalizing services, optimizing business outcomes, and ensuring customer engagement. Yet, many companies still struggle to implement data science models due to high technical barrier and limited resources.
This is where FAME, a digital asset marketplace, comes in. It offers pre-built analytics tools that can be deployed quickly, cost-effectively, and without deep technical expertise.
In this use case, we explore how the FAME project supports organizations in applying customer segmentation using RFM analysis, a powerful method to group customers based on their Recency, Frequency, and Monetary behavior.
This example highlights how two very different organizations used the same analytics asset from the FAME Marketplace to better understand their customer base and drive strategic decision-making:
Use Case 1 – Financial wellness recommendation app
This company aimed to improve its recommendation engine for families managing their finances. Using one year of customer transaction data, the RFM metrics were computed for each customer to capture key behavioral patterns, based on the following definitions:
- Frequency: Measured by the number of transactions made in the last 12 months, reflecting how often the customer engages with the service.
- Monetary: The total value of those transactions, indicating the customer’s financial involvement with the platform.
- Recency: Measured by combining the time since the last transaction and the time span between the first and last transaction, capturing both recent activity and long-term engagement.
The segmentation model identified four distinct customer groups (clusters), ranging from low-engagement users to highly active families with significant financial involvement. These segments were then analyzed to uncover shared characteristics within each group, such as common subscription plans or usage patterns, offering valuable insights to personalize and enhance the app’s recommendations.
Use Case 2 – Parking services in Athens
The second use case focuses on developing personalized payment and loyalty programs for smart parking in Athens. The goal was to build a behavioral profile for each citizen using existing app and parking data. These profiles served as the foundation for citizen-centric recommendations, such as tailored discounts on parking purchases and other personalized services.
While the final analysis differed from the first use case, the same clustering model and RFM-based data processing proved valuable in both scenarios. Using six months of app usage data, RFM metrics were computed for each user to better understand their parking behavior:
- Frequency: How often the user accessed the app to use parking services.
- Monetary: The total amount spent on parking during the observed period.
- Recency: The time since the last recorded use of the application.
The segmentation model identified four distinct customer groups based on behavior. These clusters helped reveal which types of users tend to frequent specific parking zones across Athens. By identifying the most commonly used zone for each customer and analyzing the distribution of segments throughout the city, the company was able to uncover detailed usage patterns and preferences. These insights provide a strong foundation for designing targeted offers and loyalty strategies tailored to each user type and location.
Key Benefits
These use cases highlight several key benefits of using the FAME Marketplace:
- Plug-and-play analytics: Organizations can access advanced segmentation tools without the need to build models from scratch.
- Cross-domain applicability: The same analytics asset proved effective in both financial services and urban mobility contexts.
- Scalable access to machine learning: Companies can quickly deploy powerful AI solutions, without the need for extensive infrastructure or specialized teams.
By offering these ready-to-use models, the FAME Marketplace allows organizations to make the most of machine learning and turn their data into valuable insights quickly, affordably, and with minimal technical overhead.
Author(s): Mar Galiana Fernández
—
Subscribe to our newsletter for the latest updates, and follow FAME on LinkedIn and X to be part of the journey.
More info:
ATOS
