Scrutinize Your Customers, Know Who Will Spend More

The challenge of diffused campaigns and misplaced stakes

Marketing budgets in large format retails often swell due to the huge database of target potential customers and the carpet-bombing approach they adopt. While retailers end up spending large amounts creating and executing elaborate loyalty programs and promotional campaigns, the response may be disappointing. Accurate knowledge of customers who are more likely to buy the second time can help retailers focus their efforts on this concentrated target group and derive higher benefits from promotions and loyalty marketing.

RFM model  sharpen your focus and zero in on the target

For over 30 years, direct mailing marketers of non-profit organizations have used a crude form of RFM analysis to target their mails to customers most likely to make donations. The logic was simple: people who donated once were more likely to donate again.

A number of statistical or mathematical methods help segment customers into groups. Customer segmentation method is a major and popular one in retail. However, targeted promotion campaigning and loyalty marketing is the area where RFM model is one of the most effective methods in driving incremental sales.

RFM model is a statistical method used for analyzing customer behavior and defining market segments. Used advantageously in database marketing and direct marketing, the technique has been particularly effective in the retail segment. Customer behavior can be analyzed and market segments determined based on the following vital details of purchase information:

Recency: How recently has the customer purchased?

Frequency: How often has the customer purchased in the recent past?

Monetary value: How much has the customer spent?

A customer who has purchased recently and frequently and created a high monetary value through these purchases is much more likely to purchase again. Such customers are called high RFM customers. On the other hand, customers who have not purchased in a long time tend to be comparatively less interested in the store/brand. Adding the counts for recency, frequency, and monetary value presents a good indicator of interest in the store/brand at the customer level. This is valuable information for a retail business to have.

While spending large budgets on promotions, clearance sales, offers on new products, price-offs and coupons, targeting the right customer segment can boost the success of the promotional activities. RFM analysis focuses on capturing the 20% of the customer base that is more likely to respond. The key is to identify these customers accurately. With the ever more intensive use of e-mail marketing campaigns and customer relationship management software, RFM ratings have become a critical base for the success of promotional campaigns and loyalty programs. In fact, having a loyalty program is the basis for RFM model.

How business analytics can help

Leveraging RFM model for increased sales and cost effectiveness of promotions and loyalty programs in retail is a daunting challenge. Use of spreadsheet-based manual analysis limits the amount of data to be analyzed to only a small manageable chuck, losing out on many possibilities. With humungous volumes of point-of-sales data, large format retailers need the help of business analytics to arrive at scientifically selected and segmented data.

Business intelligence (BI) solutions designed specifically for the retail industry include pre-built advanced analytical capabilities that allow the retailers to utilize RFM model as the basis for direct marketing activities including promotions and loyalty programs.

As a rule, only a small percentage (about 5%) of customers responds to offers and promotional campaigns. With the majority of customers not responding to the marketing tactics, the RFM technique helps identify the customers who are most likely to be in the responsive 5%.

Retail BI helps categorize customers based on their recency (R), frequency (F), and monetary value (M) attributes and assigns a score representing their rank. The higher the RFM score, the more profitable the customer is to the retail business now and in the future. Such high RFM customers are most likely to continue to visit the retail store and purchase. They are also most likely to respond to marketing promotions. Similarly, the low RFM customers are least likely to purchase again and least likely to respond to marketing campaigns.

Business analytics can create numerous categories for each attribute. For example, the recency attribute can have four categories: customers who purchased within the last 30 days, within 31-90 days, within 91- 365 days, and earlier than 365 days. Such categories are arrived at by applying business rules and by using data mining techniques to find meaningful breaks. With every attribute having appropriate categories defined, segments can be created from the intersection of the values.

The segmentation and behavior pattern analysis of the values can be used to determine the lifetime value of customers. Lifetime value is the expected net profit a customer contributes to the business over the customer lifecycle.

The information obtained from RFM model can be used to increase the future profitability of the retail business in several ways:

  • Identify customers with higher response predictability for various promotional activities such as targeted campaigning, customer acquisition, cross-sell, up-sell, retention, loyalty cards etc.
  • Maximize response rate while reducing overall discount costs
  • Determine the products/areas that attract high value customers and focus on them to increase customer loyalty and profitability
  • Help retention by preventing a switch to a different store brand
  • Extend the lifetime value of loyal customers


With the RFM model, enabled by retail BI solutions, retailers can save significantly on direct marketing costs and eliminate spending large funds on customers who are unlikely to respond or bring value to the business.