Applying Customer Analytics to Promotion Decisions WHITE PAPER

Applying Customer Analytics to Promotion Decisions WHITE PAPER

SAS White Paper Table of Contents INTRODUCTION... 1 MEASURING EFFECTIVENESS OF MASS PROMOTIONS.... 1 ASKING THE RIGHT QUESTIONS.... 2 GETTING THE RIGHT ANSWERS.... 2 MAKING RELEVANT CUSTOMER-SPECIFIC OFFERS.... 4 CONCLUSION... 6 RECOMMENDED READING.... 6

Applying Customer Analytics to Promotion Decisions INTRODUCTION The goal of any retailer should be to increase customer satisfaction and loyalty two elements that are essential for optimizing sales and profits. Profitable growth requires an increase in at least one of three customer metrics: Household penetration a larger number of shoppers buying items in different categories. Customer frequency increasing customer visits or trips. Spending and margin per visit higher sales and margin each time a customer makes a purchase. A critical element in improving these metrics is understanding the best promotions to offer. This can be accomplished by unlocking customer information so you can make more profitable promotion decisions. For decades, retailers had few ways to measure successful promotions. Most promotional decision making was limited to unit sales and margin. Customer activity could only be measured as total transactions. Today, it s different. You can identify and track customer purchase behavior using frequent shopper programs, private-label credit cards or customer self-identification. Now, you have massive amounts of data from which to calculate the fundamental metrics; but retailers still need help in making the best use of these rich customer insights. What follows are several ways some retailers are using customer data to improve financial results. MEASURING EFFECTIVENESS OF MASS PROMOTIONS Mass promotions are advertised specials that are made available to the general public. These specials may be communicated via mediums such as newspaper circulars, radio and television advertising spots, digital messaging or on e-commerce websites. Many of these promotions are supported by in-store signage or pop-up ads on retailers websites. Historically, retailers have focused on traditional financial metrics to determine which products to feature in mass promotions. They usually begin by reviewing which products were featured during the same period the previous year. Unfortunately, too many retailers simply reuse last year s ad, fearing they won t top last year s sales. Their process hinges on traditional financial metrics that include product and category estimates for: Unit movement. Sales amounts. Margin amounts. 1

SAS White Paper Decisions were based only on these estimates and were limited to the effect on the promoted products and sometimes on the overall product category. There was no understanding of how a promotion affects the total customer purchase. ASKING THE RIGHT QUESTIONS This traditional approach continues to be the basis for performance objectives. However, many retailers now have the data available to dig deeper into their customers behavior and answer these questions: How does a particular promotion affect the growth of customers baskets? Which customer segments respond best to promotions? How many customers, by customer segment, buy promoted products? What products do customer segments buy on promotion? How much do customers buy on promotion? How much do they spend? How many units are sold per customer? How often do customers purchase the product, or product group, when it is on special versus regular price? How profitable are customer trips or visits that include promoted products? Which customer segments affect or increase company sales and profits? GETTING THE RIGHT ANSWERS Customer metrics that answer those questions include: Customer or household penetration rate by customer segment (HHPR). Spending per trip (SPT) or per visit (SPV). Margin per trip (MPT) or per visit (MPV). Customer or household trips per week (TPW) or visits per week (VPW). Units per trip (UPT). You can use these metrics to consider your customer strategy when making promotion decisions. Which customer segments do you want to attract with the promotion? Do you want to increase customers baskets or increase the number of trips or visits? Once you establish the strategy or intent of the promotion, you can focus on the fundamental metrics: Increasing the number of buyers (HHPR). Increasing sales and profits per customer basket (SPV). Adding trips per customer (TPW). You can focus on which customer segments and which metrics matter the most for a particular promotion. Then, you can compare those metrics across promotion candidates to decide which is most likely to achieve the best results. 2

Applying Customer Analytics to Promotion Decisions For example, in Figure 1, you can see traditional financial metrics for two promotion candidates. Incremental units, sales dollars and margin dollars are estimated for Promo A and Promo B. These estimated results are calculated for the promoted items only. The promotion of choice is Promo B because that product group is estimated to produce higher incremental units, sales dollars and margin dollars. Promotion Decision Without Customer Metrics Promo A Promo B Difference Promoted Price $5.00 $5.00 $0.00 Product Group Metrics Incremental units 4,000 5,000 1,000 Incremental sales dollars $20,000 25,000 5,000 Incremental margin dollars $6,000 7,500 1,500 Figure 1. Promotion decision based on product metrics only. When you include customer metrics, however, you see wider implications for each promotion. Let s consider the metrics for two customer segments. In Figure 2, the primary customer segment makes purchases from the retailer 3.6 times per week, spends $55 each trip on average, which contributes $200 in sales each week. The secondary segment shops with the retailer less often each week and spends less each visit. Segment Trips per week Avg. basket Spending per HH per week Primary 3.6 $55 $200 Secondary 1.7 $40 $68 Figure 2. Key customer metrics by segment. From the metrics in Figure 2, the retailer might choose to focus this particular promotion on secondary segment shoppers. In Figure 3, you can see how similar promotions in the past affected the average basket for the secondary segment. If each customer in Figure 1 bought one unit of the promotion, you could assume that the HHPR for Promotion A would increase by 4 percent, whereas HHPR for Promotion B would grow by 5 percent. 3

SAS White Paper However, Promotion A generates a 2 percent increase in the average basket compared to Promotion B, which grows by only 1 percent. The average basket in Figure 3 includes sales of products from across all product categories, not just the promoted products as seen in Figure 1. Based on these assumptions, the retailer would gain $40,000 more in total incremental sales from Promotion A than Promotion B. Using these customer metrics, the retailer would likely choose Promotion A, illustrating how the promotion decisions change when the overall shopping behavior is considered. Promotion decision with customer metrics Promo A Promo B Number of secondary households 100,000 100,000 Average total basket expenditure $40.00 $40.00 Increase in average basket 2.0% 1.0% Increase in avg. basket due to promotion $0.80 $0.40 Average basket with promotion $40.80 $40.40 Total incremental sales $80,000 $40,000 Figure 3. Total incremental sales from increased average basket. A relatively small population was used in this example for simplicity, but imagine extrapolating similar results for millions of customers. You can see that incorporating customer metrics with product measurements is crucial for determining the effectiveness of mass promotions. Some retailers are beginning to use their customer data within the promotional planning process in ways similar to the example in Figure 3. You can change the outcome and improve overall profitability by considering the potential buying behavior of important customer segments when making mass-promotion decisions. MAKING RELEVANT CUSTOMER-SPECIFIC OFFERS While mass marketing continues to dominate most retailers advertising budgets, oneto-one marketing is growing rapidly. Let s explore how to improve performance by communicating directly with customers and delighting them with offers that are relevant. Personalized communications are becoming the norm. Shoppers now expect retailers to provide them with product information and promotional offers that match their needs and desires. They count on you to know their likes, dislikes and preferred communication method mobile device, email or printed media. 4

Applying Customer Analytics to Promotion Decisions On the surface, generating customer-specific offers and communications seems like an unnerving task for many retailers, but like many business problems, when broken into manageable pieces, each process step or analytical procedure is attainable. First, let s assume you have assembled promotions that you intend to extend as a group of offers (commonly called an offer bank ) to individual customers. Each offer should have a business goal or objective: Category void for cross- or up-selling for a particular product or product group. Basket builder to increase the customer s basket size. Trip builder to create an additional trip or visit to the store or an additional e-commerce session. Reward to offer an incentive for loyal customers. For example, if you want to reward loyal customers you would conduct an analysis of each customer s purchase history for each offer included in the offer bank. That analysis should consider: How often the customer shops with you and how much the customer spends. Past product or product-group purchases. Amounts spent on such products. Frequency of product purchases. Customer brand loyalty. Preference for purchasing higher-margin brands within the same category as the brand of the offer. Likelihood, based on customer-demonstrated behavior, that they would find the offer appealing. Customer price sensitivity within a particular product group. You can then apply advanced analytics to your customer assessment to produce predictive customer relevancy and propensity-to-respond scores. In addition to the offer bank and scores, you can establish business rules and contact policies to: Determine how many offers each customer should receive and whether the number differs by customer segment. Define the distribution of the offer set (e.g., the number of each offer type, such as reward, category void, basket builder or trip builder) the customer should receive. Establish offer limits or constraints that address business rules, for example:»» o Limiting the number of offers by product category to prevent offers of competing brands or similar offers from the same product group being sent to the same customer.»» o Limiting the number of offers by a manufacturer to ensure one manufacturer or brand does not dominate a customer s offer set. Define contact policies for how frequently offer types or offers from a specific product group should be sent to each customer. 5

SAS White Paper Finally, the customer relevancy scores, business rules and contact policies can be used as data input for SAS Marketing Optimization to generate the most relevant set of offers or promotions while considering an optimization goal such as maximizing overall relevancy or maximizing incremental profits. CONCLUSION The application of customer analytics in retail continues to evolve. Most retailers collect customer data and could make better promotion decisions by incorporating relevant customer metrics into their promotional planning processes. Retailers can also communicate relevant information and offers to each individual customer. Doing so requires providing merchants and other key decision makers with customer insights by incorporating customer metrics with traditional financial measures. Retailers that continue to make promotion decisions without considering measurable customer behavior are at a great disadvantage in the marketplace. Leading retailers have developed a path to success by using customer analytics to: 1. Analyze understand historical shopping patterns. 2. Measure evaluate performance over time with key customer metrics. 3. Identify discover profitable opportunities that competitors miss. 4. Predict forecast future customer behavior. 5. Optimize communicate the most relevant offers. 6. Learn, adapt and repeat steps 1 through 5. Accept the challenge to make the most of your customer data and gain a substantial competitive advantage while increasing sales and profits. To learn more about SAS customer insights offerings for retail, visit sas.com/industry/retail/customer-insight/index.html RECOMMENDED READING Shive, Wanda, and Dwight Mouton. Improving Retail Decisions with Customer Analytics: Leveraging Actionable Customer Insights across the Retail Enterprise to Build Sales and Profits. Proceedings of the SAS Global Forum 2012 Conference. Cary, NC: SAS Institute Inc. Available at support.sas.com/resources/papers/proceedings12/286-2012.pdf 6

Applying Customer Analytics to Promotion Decisions 7

About SAS SAS is the leader in business analytics software and services, and the largest independent vendor in the business intelligence market. Through innovative solutions, SAS helps customers at more than 65,000 sites improve performance and deliver value by making better decisions faster. Since 1976, SAS has been giving customers around the world THE POWER TO KNOW. For more information on SAS Business Analytics software and services, visit sas.com. SAS Institute Inc. World Headquarters +1 919 677 8000 To contact your local SAS office, please visit: sas.com/offices SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. indicates USA registration. Other brand and product names are trademarks of their respective companies. Copyright 2013, SAS Institute Inc. All rights reserved. 106653_S111618_0813