Focus On Profitable Customer.
Customer database and their historical purchase at your store are valuable information and you can mine and analysis their habit so you can differentiate them base on their loyalty. Ideally Company wants to build good Customer Relationship to their entire customer. But in this real live company resource is limited and customers we have to retain or maintain are huge. Facing this situation we have to select which and how much customer to maintain.
In common practice the company will use Pareto principal approach to select 20% customer, which contribute 80% sales. Using this approached probably will give good response when we made promotion offer to top 20% customer. By using this way we are not maximizing the power of our customer historical purchase data. Beside customer spending (monetary) we have others value information such as recently customer transaction and their frequency shopping at our store. These variables will help us to predict
which customer give higher potential response to our contact program. What the data said were three things:
- Customers who purchased recently were more likely to buy again than those customers who had not purchased in a while
- Customers who purchased frequently were more likely to buy again compare to customers who had made just one or two purchases
- Customers who had spent the most money in total were more likely to buy again.
The most valuable customers tended to continue to become even more valuable.
The idea of this concept is past purchase behavior could predict future results. First, ranked the entire customers base on these three attributes, sorting the customer records so that customers who had bought most Recently, most Frequently, and had spent the most Money were at the top. These customers were labeled as best. Customers who had not purchased for a while, had made few purchases, and had spent little money were at the bottom of the list and labeled as worst.
Promo offer information was send to the customers and the promo responses were tracked. Those customers who have highest rank and categories as best will respond to the promo compared to those customers who categories as worst. There is higher difference in response rate and sales between best and worst customers. Having this champagne over and over will give the insight of each group of customer. And probably the customer who classified as worst we could improve the response by using other promo offer approached.
Best customer segment as in the categories above always give higher response rates and generate higher sales than worst customer segment. Finding that best customer segment bring good impact to the program, than we omit the contact program to customer who categorized as worst, and spent more money to best customer segment. By improving this approach while will increase the sales will also reduce the costs and improve productivity. This will increasing marketing efficiency and effectiveness by selecting the target to the most responsive and highest future value customers.
Customers are ranked based on their historical Recentcy (R), Frequency (F), and Monetary (M) characteristics and scored them to represent their rank. Assuming the behavior being ranked (purchase habit) using RFM has economic value. The higher RFM score is more profitable customer to the business now and in the future. High RFM customers segment are most likely to continue to purchase, and to respond to marketing promotions. The opposite customer segment is low RFM score customers; they are the least likely to purchase and to respond to promotions.
As mention above RFM analysis could predict the future response. Than RFM is related to another customer marketing concept like LifeTime Value (LTV). LTV is the expected net profit a customer will contribute to the business over the LifeCycle (the period of time a customer remains a customer). Because of RFM linkage to LTV and the LifeCycle, RFM analytics can be used as a guide for the future profitability of a business.
High RFM customers segment represent future business potential, because the customers are willing and interested in doing business to company and have high LTV. While low RFM customers represent dwindling business opportunity, low LTV, and are a flag something needs to be done with those customers to increase their value.
Once you have finished with customers scoring using RFM analysis, you will be able to:
- Decide whom to promote to and predict the response rate
- Optimize discount promotional by maximizing response rate and reducing overall discount costs
- Understand which activities attract high value customers and focus on them to increase customer loyalty and profitability.
