Find and Understand Your Most Valuable Customers
From your transactional data you already know which customers drive the biggest revenue for your business. With a deeper understanding of the segments they match you can effectively develop your marketing and sales strategy
You also get an overview of how many twins your most valuables customers potentially have; for your data-driven business strategy and targeted marketing to more high value prospects
With our customer analysis we supplement the classic RFM analysis with insights into the value groups as customer segments when we blend your transaction data with several external data to provide you with a 360° portrait of your customers
You get an overview of your market potential and the remaining potential based on your excisting customer base and transaction data. This knowledge is supplemented by data on your customers' characteristics within socioeconomy, values, and attitudes towards consumption and society to improve the value and effect of your customer segmentation
Know Your Value Groups and Customer Segments
An RFM analysis (recency, frequency, monetary value) provides you with a data-based foundation to uncover
• your customers' buying patterns
• your customers' characteristics divided into value groups
The results of the analysis ensures your data foundation for decision on sales' tactics for certain segments, sales messages, product development and, not least, choose the customer segments you would like to further analyse, e.g. with a potential score
By blending your transaction data with our extensive database you get to know your customers segments'
- demographic characteristica like family type, age distribution, car ownership and finances
- consumer habits: do they chase offers, prefer well-known brands or favour new products?
- preferences: do the prefer organic goods, luxury, or discount?
"The prioritisation of subjects based on modelling has not only improved our contract rate and average sale pr. customer but also made sure that we have a higher return on acquisition of new customers"
- Jørgen Thau, Tryg
How the Analysis is Done
Your customers are divided into value groups based on a FRM calculation; based on your transaction data your customers are divided into value groups based on their latest purchase, purchase frequency, and the value of their purchase on a scale 1 to 5. We use the average value per purchase, i.e. the average number of days since last purchase (Recency), average amount of purchases (Frequency), and the average value of a purchase (Monetary value)
Your customers are then ranked based on their value within each of the categories recency, frequency, and monetary value and assigned a score. The sum of the scores is the RFM score for the customer. That means that even though a customer might shop frequently and for a large amount of money the RFM score is adjusted if it has been a while since the customer's latest purchase
The customer based is then sorted and divided after the RFM score into five groups which are then collected in three aggregated groups; high value, medium value, low value. For clarity these are the three groups then described as customer segments
• There should be at least 1000 rows in the input file containing the customer tranactions to get a valid result. The file should contain the customers's address and information on purchase data and sum. If you know the age of your customers this can also be included in the calculation and further increase the precision of the analysis
• Files are uploaded in an Excel format
• Your data are analysed and blended with Geomatic's data
What You Get
The output is a PowerPoint presentation defining and describing the value groups in you customer base and the three value groups described as customer segments based on buying behaviour, geography, and the demographic characteristics of your customers
If you opt-in to get it, you also receive a copy of your customer file enriched with an RFM segment on each customer ready for upload into your CRM or to integrate into your analytics
file_downloadSee an example (DK report)