Forecasting Provides Fundamental Insights at Staples

SAS Saves Millions for Office Supply Superstore

How does a successful retail corporation with nearly 1,100 U.S. stores and $11 billion in annual sales decide where to open new stores each year? For Staples Inc., the answer is easy – with SAS. SAS' forecasting capabilities help analysts at the office supply superstore calculate three years' worth of sales forecasts for nearly 5,000 potential store locations each year. Staples executives use the results to help determine the best site for each new store.

Alan Gordon, Director of Sales Forecasting at Staples, counts on SAS to evaluate real estate sites using historical sales data and customer demographics, including the business and household data, the quality of real estate locations and the level of competition.

The results of Gordon's forecasts have refined Staples' real estate strategy for the past eight years, saving the company millions of dollars by avoiding bad real estate decisions. "If our real estate model keeps us from making just one bad decision per year, we pay for the cost of this entire department about five times over," says Gordon. The costs for shutting down an existing store can range between $500,000 and $1 million, explains Gordon.

But the benefits of Gordon's analyses don't end there. When he built the real estate model in 1994, he first had to develop a forecasting system that delivered sales projections for each of the company's stores. It started as a small project – predicting annual sales figures for 150 stores. But the SAS solution has scaled and expanded with eight years of tremendous growth at Staples.

Today, SAS collects and examines eight million data transactions each week, so Gordon and his team can forecast weekly and daily sales for more than 1,100 U.S. stores. And the data is used throughout the company for everything from forecasting seasonal sales and scheduling labor to managing inventory and estimating annual budgets.

"The potential uses for these forecasts are just amazing," says Gordon. "Our use of SAS is very far reaching." In fact, his forecasts are available to finance executives, marketing analysts and store managers throughout the company every day.

Targeted Marketing Results Improved
The most recent and most exciting use of the forecasts, according to Gordon, is in the marketing arena. Staples' marketing analysts are combining their targeted marketing results with the real estate models and mining the results to determine the best ways to attract customers from different zip codes.

"There are a lot of factors in the real estate model that we can use to understand who's going to respond to a particular offer, and who isn't," says Gordon. "Basically, we've added geography to our marketing models, as a new way to target customers, further leveraging the investment in our forecasting systems."

The project is in the preliminary stages, but Gordon's models have already reduced the costs for each marketing campaign by 25 percent. More significant, however, are the increased response rates for direct mail campaigns, which have improved significantly when data from the real estate model is employed.

"When I think about all the things that we could do with SAS, I know we're just scraping the surface," says Gordon. He's especially excited about the zip code targeting. "We've done a couple of campaigns with that, but there are so many ways we could take that going forward. We could really build more powerful models based on what we know about the customer and what we can add to the model."

Knowledge that Drives the Business
When Gordon began building the sales forecasting system eight years ago, he says SAS was the obvious choice for forecasting and data analysis. "What I like about SAS is that we're able to use the same product to analyze the data and to build systems that make use of those analyses. SAS gives us the ability to build and deploy systems that quickly make use of our company's data."

Gordon also praises SAS for its usability, scalability and openness. The sales forecasting department recently began converting from an Open VMS platform to an HP UNIX platform, but SAS is making the transition easy.

"Openness is important," explains Gordon. "We even have some data in Access databases, but SAS just goes and grabs the data, does all the serious processing and pushes the SAS data sets onto VMS, then over to UNIX. It can even load files into the GIS system that our real estate analysts use, so every aspect is coordinated. It's a tremendous advantage to be able to take the same code and run it through different places."

Most importantly, Gordon says, "We use SAS because it's a great analytical solution. It gives us the powerful analytics that we need to really understand and manage all the different things that influence our business."

And he foresees a continued reliance on SAS for forecasting and analysis. "SAS will continue to help Staples understand how our business is performing and where it's going. That's always been the bottom line for us – to understand as much as we can about the business so that we understand where we have been and know where we are going. With SAS, we gain knowledge that really tells us what drives our sales and what makes our forecasts work."

The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Copyright © SAS Institute Inc. All Rights Reserved.