A comprehensive environment for more efficient forecasting

Jessica Dunn was already sold. Dunn, a Bank of America Vice President who helps coordinate the planning, forecasting and performance of the bank's credit card services, was already a longtime SAS user when the credit card services division began investigating new business intelligence products that would help provide more efficient forecasting in particular and more informed business decisions in general.

Dunn is among some 4,000 SAS users at Bank of America, as is everyone else in her group. “We’ve been using a number of SAS tools since I came to the bank seven years ago,” she said. “I've seen other software packages come and go, but SAS stays.” The decision was made to introduce SAS 9.2 with the core components of the SAS Business Analytics Framework.

The objective was to have the solution fully functional by the end of the year – an objective that was met.

SAS Enterprise BI Server – specifically, web reports and dashboards – has reduced my monthly reporting duties from three days to three hours.

David Ribar
Vice President, Consumer Product Strategic Analyst

Today, Dunn said, "SAS has really changed the way we're doing business."

"I use it every day," said David Ribar, a fellow VP who provides actual-versus-forecast reporting for executives. "I use SAS to access and filter through millions of rows of data.

"The SAS® Enterprise BI Server – specifically, web reports and dashboards – has reduced my monthly reporting duties from three days to three hours."

Building cubes a 'big win'

"Our first big win," Dunn said, "was when we started building our own cubes. Typically, we would go to a group within the bank and have them build our OLAP cubes, and it could take up to four months."

In the meantime, her group would have to provide, on an ad hoc basis, large data sets to meet the needs of its internal clients.

"So now, having that skill set within our team – being able to go in and build the cubes with multiple hierarchies within a day or two – has been a huge efficiency gain. Previously, if we had a change in our value matrix, it could take us a couple of months for those changes to reach our partners. Now the change is seen within a couple of days."

What's more, the data can be placed in any format requested.

No hang time

The SAS Enterprise BI Server has been a game-changer for Dunn and her colleagues. The software integrates the power of SAS Analytics and data management with centralized administration.

The primary objective of this deployment was more efficient forecasting, and Dunn said, "Our finance partners were extremely excited about what we were offering them. We built an application that really helps them with their forecasting."

"The thing about the SAS solution is that there are so many ways to do things. We kept on trying different ways. We built a process that incorporated a forecasting method that's already behind the scenes before the analysts even see the data."

The SAS solution also provides more efficient quality control with a process that Dunn said will routinely save two to three weeks of work.

Previously, forecasters would have an Excel workbook for nearly 200 value-matrix segments. Once they made their changes, forecasters would upload the Excel documents into a Microsoft Access database, "which just took hours," Dunn said. If they needed to make a change once everything was in the Access database, they had to go back, open up every Excel document, make the change, save it back out and then upload it again to access it and see if their change was what they expected.

Dunn said that one business partner told her it took a half-day to recalculate one change. "No more of that. There's no hang time, no waiting."

Now all the data is pulled into the SAS Enterprise BI Server, a forecasting methodology is applied, all the financial inputs are merged with the data, there are quality-control checks and the data is pulled into one Excel document. Then the forecasters can begin manipulating the data. "They use it as a sandbox," Dunn said, "because they're most comfortable there. We then take the data and put it back up on the SAS Enterprise BI Server."

Dunn can put data out in the environment in which the forecasters are most comfortable, and "they're not even aware that SAS is running behind the scenes. They don't have to be programmers; they don't have to understand the code. The whole process is seamless."

More time for what's important

"Not only does SAS make my job easier," Ribar said, "it makes it possible."

Previously, he would run SAS, load the data into Excel, then copy and paste it to build reports in PowerPoint.

"It was tedious," he said. "Now I just run my monthly queries and the web reports are automatically updated. That frees me to spend more time analyzing the data."

A wide range of users, from executives to analysts, take advantage of the reports Ribar produces, and each can now very easily point and click and get the specific information they want to view. And if he's provided line charts and they'd prefer to see bar charts, they can easily change it.

"He really has it built in a way that meets a wide range of his audience's needs," Dunn said.

The next step, Ribar said, will be to utilize the SAS add-ins for Excel and PowerPoint to create automated reports in those applications.

"For my own research and debugging," he said, "I work entirely in SAS. But for deliverables, I export data to Excel using PROC DOWNLOAD and PROC EXPORT and create my final tables and graphs there."

Dunn and Ribar have also both appreciated SAS® Enterprise Guide®.

"It's funny, but the people on my team I would have said wouldn't like SAS Enterprise Guide, because they're all coders, really have loved using it," Dunn said. "Now we can map out the flow."

Dunn said SAS Enterprise Guide makes code visually appealing and the process easier to understand. "We share projects back and forth all the time now instead of just code. So I think SAS Enterprise Guide has been our biggest surprise – the thing we enjoy the most."

The edge

The SAS solution's most attractive feature, though, Dunn said, is the "ability to do everything in one place" – to do predictive modeling, forecasting, create interactive dashboards and present data in the ways that make most sense to her colleagues and top management – a concise solution in which one function blends into the next.

Then there's the partnership. Dunn said that the relationship her Bank of America group has forged with SAS has been critical to the success of this project and its timely completion.

"We definitely couldn't have gotten this project completed by the end of the year without that partnership with SAS. As I told our leadership team, when we hired a consultant from SAS we not only got an on-site person; we got a whole team behind him. And we've utilized that whole team, from the account executives to research and development to professional services. I mean, we've really leveraged that whole support system."

"We're now going to be taking advantage of what this platform offers us and building more custom tools in 2011," Dunn said, "more around our risk and shareholder values of returns – building more decision tools, more tools for the investment side of the value matrix."

Dunn believes the solution provides a true competitive edge.

"We're working smarter now," she said. "We're more efficient; we're not losing time tracking where the problem lies anymore – we're working on the solution."

A number of other Bank of America groups have now taken an interest in what Dunn and her team are doing: "We think this is going to be the analytical platform that a lot of our teams are moving toward."

Dunn said that she and her team were tense at the outset when they were told, "You want to build this? You want to use this new SAS Enterprise BI Server tool? OK; but you have to have it done by the end of the year."

"We'd never built anything like this before. We didn't know how long it was going to take, but we knew we had to be finished by the end of the year. We made it."

"People are excited about this product and we're excited with them," Dunn concluded. "We have a sense now of what this tool can do, but we've still only touched the surface. Now we want to start customizing some of the products within the SAS Business Intelligence suite, and that's where it's going to get really exciting."



Fulfill client requests for forecasts in much less time and with greater accuracy, reliability and efficiency.



  • Forecasts are ready in days, even hours – not months.
  • Quality-control processes are automated and more efficient.
  • Forecasters now spend their time creatively and proactively supporting clients rather than responding to tedious, time-consuming processing needs.
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.

Back to Top