Increase Revenue and Improve Business Strategy with Retail Analytics

Posted by Daniel D. Gutierrez on Mon, Apr 07, 2014

OS SC Retail Analytics GP 2014 V1.6 09

When people shop online, they know they’re sharing personal data to be collected and used for marketing purposes. And yet we’re surprised by how many companies fail to do even the bare minimum of analysis with the data they’ve painstakingly gathered. By implementing just a few basic analytics techniques into your marketing practices, you can quickly gain insight into your site’s performance, your customers’ satisfaction, and the effectiveness of your marketing campaigns. And if you take your analytics a few steps further, you can actually predict what your customers want and gain specific recommendations about how best to market to them — whether you have hundreds of customers or millions of them.

Here, we’ll show you the basic building blocks of retail marketing analytics. The insights gathered from these techniques can help you optimize business strategies and increase revenues. We’ll show you which metrics, or key performance indicators (KPIs), matter the most and how they can be used to measure the success of a retail enterprise. We’ll also shed some light on what’s possible once you establish the basics: the more advanced analytics techniques that deliver predictive insights and recommended actions. Your crash course starts now.

Cost per Acquisition

Cost per Acquisition (CPA) is a vital KPI that gives insight into the cost of acquiring a customer. CPA helps gauge a marketing campaign’s impact because there’s a distinct economic cost associated with getting a customer to visit your company’s Website. There are many common strategies for attracting a customer, including organic search, pay-per-click advertising, and social mentions, not to mention word-of-mouth referrals. 

Cost per acquisition (CPA) is calculated by taking cost (amount spent on marketing) divided by the number of acquisitions (the number of customers who make a purchase). For example, if you spend $2,000 on a pay-per-click ad campaign, and you manage to acquire 80 new customers, then your CPA is $25.

You also can granulize your CPA analysis by doing the calculation along the lines of specific marketing channels to determine which ones are performing the best. CPA then becomes an optimization problem in maximizing well-performing channels while minimizing the use of low-performing ones. 

Down the line, you can use CPA along with a multiple linear regression algorithm to determine a trend against various predictor variables, such as marketing budget, number of channels, duration of campaign. You can also apply nonlinear optimization techniques to maximize the effectiveness across all acquisition channels, improving return on investment.

Customer Lifetime Value

The Customer Lifetime Value (CLTV) KPI is focused on keeping customers rather than acquiring new ones. This KPI helps determine the true value of repeat customers in that it predicts the entire future economic value of a customer. Retailers can approach CLTV in different ways — all customers, customers in specific geographical regions, customers in specific sales channels —to determine the company’s most profitable customer segments.  

Customer lifetime value (CLTV) is calculated by multiplying three values: average value per sale, number of repeat transactions, and average retention time (months or years) for a customer.

A possible opportunity for using CLTV is to deploy a nonlinear model, such as polynomial regression, in which the relationship between the predictors and the response is nonlinear. This would tell you, for instance, whether a customer's value changes with the season. Then you can use that information to increase marketing campaigns during low activity seasons.

Churn Rate

Churn rate is an important KPI for many classes of business. You usually hear churn rate discussed with respect to the Software-as-a-Service (SaaS) business model which depends on recurring subscriptions. But churn also is important for retail establishments that need to understand why a customer makes a purchase and then never returns. Tracking these one-time customers is another form of churn. Instead of subscriptions, where there is a hard cutoff date when the customer cancels their subscription, for retail it’s important to view the churn rate with respect to a period of elapsed time since the customer’s last purchase. The specific elapsed period you choose depends on your business insights in understanding the length of time most customers will wait until returning to make another purchase. It could be 30 days, a quarter, or even a year depending on the business. The churn rate would apply to any customer that did not return within the selected elapsed time period. 

Churn rate is calculated by dividing the total number of one-time customers by the total number of customers. Businesses treat churn rate as an optimization problem to minimize the rate to achieve optimal results.

With a reliable churn rate KPI, retail businesses can run strategic experiments with different marketing programs to see what impact they have on churn. One particularly useful insight that can be gleaned from understanding churn is how different customer segments comprise the overall churn rate. It may be possible to target specific segments with custom promotions (e.g. discounts, free shipping, etc.) or loyalty programs that may reduce churn.

It is also possible to predict when customers are about to churn, using a logistic regression machine learning algorithm, for example, allowing you the opportunity to take some sort of action to prevent it, such as offering a special discount.

Other Retail KPIs

Additional KPIs are well-suited for retail businesses. Each provides a deeper level of understanding of the relative health of the business:

  • Sell-through rate — the percentage of inventory taken from suppliers that’s actually sold to customers. Obviously, a higher sell-through rate means better performance for the retailer.
  • Sales/gross margin —the amount a retailer earns from the sale of goods before subtracting out cost of goods sold (COGS). This percentage is important to retailers in that a healthy gross margin means that a retailer is able to pay its operating costs and generate a profit.
  • Inventory turnover — the lifeblood of a retailer is the ability to turn over inventory, i.e. the number of times inventory is sold in a year’s time. Tracking the turnover rate over time is important to gain insight into how fast inventory is turning over versus a past period.

These KPIs, combined with machine learning algorithms  can help predict future trends.

Building a Retail Analytics Web App

One method of exposing the above metrics in a convenient way for management decision making is to build a simple Web-based application. Here is a recipe for developing one or more apps to track metrics over time:

  • Use the R statistical environment to access data in your marketing department data mart or enterprise data warehouse. You can easily do this using the sqldf package for R.
  • Perform some exploratory data analysis to discover factors like cutoff date for determining the churn rate described above.
  • Define a set of R functions to calculate the metrics like LTV over a selected time increment (number of months).
  • Use a linear regression model to detect trends, or build a decision tree classifier to detect likely churn.
  • Use the Shiny tool to expose your R scripts and plots on the Web for management to interact with and make decisions.


Intelligent retail analytics can — and should — become an integral part of your company’s decision-making process. By developing and expanding your toolbox of important retail KPIs, you’ll be able to gain insights into key elements of your business and more intelligently make decisions to increase revenue and improve business strategy. The trick is to identify the metrics best able to capture your business goals. This toolbox should be a good starting point.

Download our Transformative Analytics White Paper to learn more.

Download Now




Daniel D. Gutierrez is a Los Angeles–based data scientist working for a broad range of clients through his consultancy AMULET Analytics.


Topics: Big Data, Data Science, Analytics, Signals, Marketing