Does your extended supply chain suffer from extreme seasonal variability? Does this situation challenge your ability to meet service level commitments to your customers? I have grappled with this at Rev-A-Shelf, addressing unusual conditions created by Chinese New Year and other global events, and would like to share the experience and a few things I learned along the way.

First, let me explain our situation. We import 60% of the parts we use to build our kitchen and bath accessories from China and Europe. Most of the year we were able to plan our inventory needs using a spreadsheet-based min/max approach. But not during Chinese New Year, which drives the planet’s greatest annual population migration. Chinese New Year shuts down production for up to two months, creating significant supply risk as we strive to meet our three day order fulfillment commitment.

We solved our problem, introducing statistical demand forecasting with the flexibility to extend lead times when necessary, the ability to reliably establish safety stocks that achieve our required service levels and a continuous reporting system that lets everyone know exactly where we stand. However, success required much more than a new piece of software. We needed to change the way we view future demand, supply risk and safety stock. Here are a few key things we did that made all the difference.

Stakeholder education and buy-in

Regardless of the project, it’s always best to enlist the buy-in of all stakeholders. We knew we had to do something to solve our problem, but there was bound to be resistance. Senior managers, for example, had developed a healthy distrust of software and wondered whether demand forecasting software could help. Our buyers had developed their own perspectives and procurement methods, and felt personally at risk as we considered new approaches.

People came around as they developed a common understanding of the problem and how we would address it. Education was a big part of the solution. We explained how forecasting works and key factors we should all understand: how to analyze trends, how to use “what if” scenarios, impact of shifting lead times, how to relate service levels to supply risk and safety stock and key performance indicators like inventory turns. Going through this process together, we all became stakeholders in the solution.

Use the Right software

When you have lots of part numbers and any sort of supply or demand variability, you just cannot forecast effectively with a spreadsheet. With our min/max forecasting system, we were planning to an average, and it wasn’t working. Average usage has inherent flaws for planning purposes—it’s always looking backward!

You need software that looks ahead, recognizes seasonal patterns and enables you to determine how much stock you’ll need to meet required service levels over varying lead times.

Fine-tune processes

When the old ways don’t work, you need to be open to adjusting your assumptions. Think less about where you’ve been, and more about where you want to be. Take a look at your lead times and plan to your desired service level. Last year’s history may not be the best predictor of this year’s demand. The same forecast horizon may not be appropriate for all products or certain time of the year.

Make the Forecast Actionable

It’s not enough to produce an accurate forecast and estimated inventory stocking levels. You’ve got to develop a way to make the information actionable for those tasked with using it. We developed a set of reports that enabled buyers to leverage better forecast and safety stock information. Now, at the end of every month, we produce a forecast report that provides a clear picture of current inventory, safety stock, past usage, forecasted usage, incoming deliveries (PO’s) and recommended order quantities.

Validate Results

You can, and we did, test our new methods against our own demand history. Still, an authoritative outsider can make acceptance easier. We commissioned a study by a professor at Louisville University’s College of Business who set one of her graduate students to the task. Through them we were able to reinforce what we saw happening from our results, and feel comfortable that we were on a good path.

All of these factors helped Rev-A-Shelf transform its demand planning process, to great effect. Today we are exceeding our service level targets, and our fill rate, based on a three day ship cycle, is showing steady improvement, and trending up. Overall, units-in-stock have stayed flat while supporting a 13% increase in sales

John Engelhardt is currently Director of Purchasing and Asian Operations for Rev-a-Shelf, LLC in Louisville, KY. He has held a variety of management positions both in private business and public organizations. At Rev-A-Shelf he held the position of International Sales Manager and Director of Sales Support before assuming his current position. He can be reached at johne at rev-a-shelf dot com.

Most statistical forecasting works in one direct flow from past data to forecast. Forecasting with leading indicators works a different way. A leading indicator is a second variable that may influence the one being forecasted. Applying testable human knowledge about the predictive power in the relationship between these different sets of data will sometimes provide superior accuracy.

Most of the time, a forecast is based solely on the past history of the item being forecast. Let’s assume that the forecaster’s problem is to predict future unit sales of an important product. The process begins with gathering data on the product’s past sales. (Gregory Hartunian shares some practical advice on choosing the best available data in a previous post to the Smart Forecaster.) This data flows into forecasting software, which analyzes the sales record to measure the level of random variability and exploit any predictable aspects, such as trend or regular patterns of seasonal variability. The forecast is based entirely on the past behavior of the item being forecasted. Nothing that might have caused the wiggles and jiggles in the product’s sales graph is explicitly accounted for. This approach is fast, simple, self-contained and scalable, because software can zip through a huge number of forecasts automatically.

But sometimes the forecaster can do better, at the cost of more work. If the forecaster can peer through the fog of randomness and identify a second variable that influences the one being forecasted, a leading indicator, more accurate predictions are possible.

For example, suppose the product is window glass for houses. It may well be that increases or decreases in the number of construction permits for new houses will be reflected in corresponding increases or decreases in the number of sheets of glass ordered several months later. If the forecaster can distill this “lagged” or delayed relationship into an equation, that equation can be used to forecast glass sales several months hence using known values of the leading indicator. This equation is called a “regression equation” and has a form something like:

Sales of glass in 3 months = 210.9 + 26.7 × Number of housing starts this month.

Forecasting software can take the housing start and glass sales data and convert them into such a regression equation.

Graph displaying a relationship between example figures for time-shifted building permits and demand for glass
Leading indicators demonstrated
However, unlike automatic statistical forecasting based on a product’s past sales, forecasting with a leading indicator faces the same problem as the proverbial recipe for rabbit stew: “First catch a rabbit”. Here the forecaster’s subject matter expertise is critical to success. The forecaster must be able to nominate one or more candidates for the job of leading indicator. After this crucial step, based on the forecaster’s knowledge, experience and intuition, then software can be used to verify that there really is a predictive, time-delayed relationship between the candidate leading indicator and the variable to be forecasted.

This verification step is done using a “cross-correlation” analysis. The software essentially takes as input a sequence of values of the variable to be forecasted and another sequence of values of the supposed leading indicator. Then it slides the data from the forecast variable ahead by, successively, one, two, three, etc. time periods. At each slip in time (called a “lag”, because the leading indicator is lagging further and further behind the forecast variable), the software checks for a pattern of association between the two variables. If it finds a pattern that is too strong to be explained as a statistical accident, the forecaster’s hunch is confirmed.

Obviously, forecasting with leading indicators is more work than forecasting using only an item’s own past values. The forecaster has to identify a leading indicator, starting with a list suggested by the forecaster’s subject matter expertise. This is a “hand-crafting” process that is not suited to mass production of forecasts. But it can be a successful approach for a smaller number of important items that are worth the extra effort. The role of forecasting software, such as our SmartForecasts system, is to help the forecaster authenticate the leading indicator and then exploit it.

Thomas Willemain, PhD, co-founded Smart Software and currently serves as Senior Vice President for Research. Dr. Willemain also serves as Professor Emeritus of Industrial and Systems Engineering at Rensselaer Polytechnic Institute and as a member of the research staff at the Center for Computing Sciences, Institute for Defense Analyses.