Analyzing the Customer Database

What you’ll learn to do: Examine the objectives for analyzing the customer database

We will explore some of the techniques behind customer retention and customer loyalty programs. How does a retailer identify their best customers? What is market basket analysis and how does it help retailers tailor their product mix? How do retailers leverage their information systems to retain their best customers? What are the tactics used in a customer loyalty program?

Identifying Best Customers

We have seen how the development of powerful CRM systems can provide valuable information to retailers. The more any business knows about their customers, the better they can meet their needs. This is even more crucial for retailers as they must anticipate demand in advance and invest in goods prior to demand.

Using data analyzed from their CRM system, retailers can drill down to find their best customers. The definition of “best customers” may vary from company to company, but in general businesses look for purchase frequency, average purchase amount, lack of returns, response to survey requests, positive reviews on surveys, and posting positive opinions on social media. Further, retailers can learn even more about their best customers by engaging with them using “Relationship Marketing” techniques.

Relationship marketing is a facet of customer relationship management (CRM) that focuses on customer loyalty and long-term customer engagement rather than shorter-term goals like customer acquisition and individual sales.

One-to-one marketing is a CRM strategy where service is personalized for every customer in order to foster customer loyalty. One-to-one marketing has become even more prevalent with the increase in online shopping. Companies like Netflix, eBay, iTunes and Amazon record every single customer click and categorize every purchase in order to construct a detailed customer profile. With that data, these online retailers are able to construct individual marketing plans for each customer

Goals of Data Analysis

Market basket analysis gives clues as to what a customer might have bought if the idea had occurred or been suggested to them. Other terms used are “impulse purchasing’ or “cross selling” to describe this consumer purchasing behavior.

The availability of detailed information on customer transactions has led to the development of techniques that automatically look for associations between items that are stored in the database. An example is data collected using bar-code scanners in supermarkets. Such ‘market basket’ databases consist of a large number of transaction records. Each record lists all items bought by a customer on a single purchase transaction. Managers would be interested to know if certain groups of items are consistently purchased together. They could use this data for store layouts to place items optimally with respect to each other, they could use such information for cross-selling, for promotions, for catalog design, and to identify customer segments based on buying patterns.

Market basket analysis can be used as a first step in deciding the location and promotion of goods inside a store or on a web page. If, as has been observed, purchasers of Barbie dolls are more likely to buy candy, then high-margin candy can be placed near to the Barbie doll display. Customers who would have bought candy online might be tempted with Barbie doll images popping up on web page margins. The infamous “would you like fries with that” phrase is an example of the association between products that market basket analysis can reveal.

The computational complexity involved in calculating the results of market basket analysis is a challenge met only with DW and data mining techniques. With data warehouses storing billions of transaction lines, so-called "big data" tools are needed to draw meaningful conclusions. Special techniques involving filtering or aggregating parts of the transaction database are commonly used to create performance algorithms to allow some level of interactivity, such as what-if queries and scenario creation in business intelligence applications.

Market basket analysis is a strong tool in the retailers’ arsenal to increase sales using the latest data analysis techniques. Once out of reach, sifting through mountains of data to draw empirical conclusions can lead to effective assortment plans–determining the appropriate product mix—and promotional opportunities to cross-sell.

Frequent-Shopper and Rewards Programs

Customer retention is crucial to the success of any business given the high cost of acquiring a customer in the first place. It is estimated that it costs a business 5-25X more to acquire a new customer than to sell to an existing one. Further, established customers are thought to spend 67% more than new customers.^[3]

It’s no wonder that savvy businesses have brought a variety of customer retention techniques together under the umbrella of formal “Frequent Shopper” or “Customer Loyalty” programs. As consumers, we all experience these techniques every day.

Some programs are based on simple point system–a purchase amount is equivalent to a number of points. Those points can then be accumulated and used as currency to make additional purchases.

A variant of this tactic, a so-called tiered reward program, is designed to foster longer-term loyalty. Airlines and car rental companies offer such programs and consumers move up the food chain by becoming Bronze, Silver and Gold members over time. With each designation, the customer receives more benefits and perks.

Another tactic is charging customers an annual fee in exchange for VIP treatment. Amazon Prime would be a good example of this type of customer loyalty program. “Prime” customers pay an annual $99 fee to participate in the program.  As Amazon Prime members, customers receive free two-day shipping on millions of products with no minimum purchase required.  According to the Consumer Intelligence Research, Prime members spend an average of $1,500 per year on Amazon.com, compared with $625 per year spent by Amazon customers who aren't Prime members.^[4]

Customer Retention Techniques

Based on the CRM data of their customers, retail businesses use multiple techniques to encourage customer retention. We are all willing or unwilling participants in these activities on an everyday basis. Your morning email inbox is stuffed with news or offers regarding some sale or incentive from your favorite retailer. Your trip to the gas station may involve a reduced gasoline price based on your prior food shopping trip. When you pick up gardening supplies on your way home from work, you are asked for your rewards number and personalized discount coupons are then generated for future purchases.

Customer retention techniques can start simply with soliciting customer feedback after each interaction with the company to learn ways to improve the customer experience. Often, a customer purchase from a retailer is rewarded with an incentive to purchase again. As the retailer learns more about their customers’ preferences, more communication can be initiated in the form of notifications of upcoming sales events, additional discount offers, cross-marketing campaigns involving related products, etc. This series of actions and responses is sometimes referred to as “High Touch” marketing.

Grocery retailer Kroger retains customers through a “preferred customer club.” To join, customers must provide their contact information and in turn receive a membership card. With every purchase, customers swipe their card enabling Kroger to record and categorize every transaction. This allows the retailer to offer coupons and promotions for their favorite frequent purchases.

Licenses and Attributions