A telecom value-added services(VAS) company sends out 30MM SMS’s to its customers every month. The average response rate on such campaigns has been close to an abysmal .5%.  Still the company persists as the cost of sending the SMS is quite low and the campaign did push the sales. But, increasingly, telecom companies are becoming reluctant to barrage their customers with mass messages. The customers are getting tired, so are the telecom companies. Last month, the VAS company decided to create more targeted offerings through customer segmentation. They did an RFM analysis for their customer base and segmented the population into 64 groups. Then they ran a campaign on 1% of the customer base (300k customers) and learnt the response rates for each of these segments. This month the company sent out messages to 5MM  customers instead of 30MM (12 out of 64 segments). Response rates were a phenomenal 2.7%. The company got almost the same no. of responses by targeting just about a sixth of the population. The company’s profitability increased. The telecom operator was happy and so were the customers.

Direct marketers all over the world are discovering the power of this wonderful tool: RFM analysis

What does RFM stand for?

RFM Analysis

●      Recency – How recent was the last purchase?

●      Frequency – How many purchases have been made?

●      Monetary Value – What is the value of the purchases?

How does it work?

RFM is based on a combination of common-sense and empirical evidence. Customers who have purchased from you recently are more likely to respond to a new offer. Frequent buyers respond better than less frequent buyers. Customers who make high-value purchases are more promising prospects for marketers.

Recency is usually the strongest differentiator but depending on the type of business you are in, frequency and monetary value would vary in importance. For example, a mutual funds company may find monetary value to be a strong differentiator.

What are the benefits of RFM?

RFM analysis segments the customers according to their attractiveness thus helping the marketing team decide on the optimal utilization of marketing spend. A company may want to target only the most attractive customers. It may also want to design a program to migrate customers from less attractive segments to the more attractive ones.

The RFM model works in practically any kind of high activity business.  And it works for just about any kind of behavior you are trying to get a customer to repeat, whether it’s purchases, visits, sign-ups, surveys, games or anything else.

RFM has an interesting use in customer acquisition strategies. Once the customer base has been segmented, attractive segments can be profiled along geo-demographic information to build a profile for the ‘ideal customer’. Once a retailer has a clear picture of its ‘ideal customer’ all marketing effort can be tuned around this profile.

Use RFM carefully

RFM analysis can be like a self-fulfilling prophecy and therefore great care has to be taken while using it. RFM can make you focus on your most responsive customers, forgetting the non-responsive ones. While this may boost response initially, eventually a retailer may end up losing some customers who get ignored repeatedly. While its ok to lose the unprofitable customers, it is imperative that other customers should be encouraged to migrate from low-value segments to high-value ones.

Do not over-market to the good customers. You don’t want to wear out your welcome with a barrage of promotions to these valuable customers.

Used sensibly, RFM can be an effective marketing tool. It is good for quick results – it can provide immediate response lifts. But its long run effectiveness lies in combining it with other initiatives especially those around migrating customers into the high-value segments.

Interested in learning about other Analytics and Big Data tools and techniques? Click on our course links and explore more.
Jigsaw’s Data Science with SAS Course – click here.
Jigsaw’s Data Science with R Course – click here.
Jigsaw’s Big Data Course – click here.
SHARE
share

Are you ready to build your own career?