by R.T. "Chris" Christensen

Now that I have your attention from the catchy headline, let me be the first to break your bubble. There is no way to make forecasting easy.

What I am going to do over the next few articles, though, is describe the different types of forecast tools, along with their strengths and weaknesses.

Forecasting isn’t easy, but with the right forecast tool, you can make a serious impact on your forecast capabilities. I won’t be talking about the different software programs available as forecasting tools. There are so many of them that just listing them would be nearly impossible.

What I will do is provide a discussion of the different types of forecasting methods. This means that I will show you how the calculations work, so that you get an understanding of how the math is done. This way, you can determine the forecast system that best fits your company and its needs.

A few things are needed to help us get started in looking at developing a forecast tool that is suitable for your operation.

One thing you need to do is examine the possibility of using more than one forecast tool. Most consultants or systems providers will generally try to use the same forecast tool for all your needs.

This generally does not work well. What it does is make the consultants’/system providers’ life easier because there is little effort in the implementation process and a high return in the consulting fee. It’s a good revenue-generating tool for them and you are paying for it.

So, why shouldn’t you get a one-size-fits-all tool? It’s your money, so why not select the best forecast tool that fits the different classifications of your inventory?

If you follow this Coach series, you’ll remember reading the piece on categorizing inventory by use rate and cost (visit Coach Christensen's archives on this site to refresh your memory). This is the A/B/C classification, and what we do is separate the significant few from the trivial many.

Studies have shown that 80 percent of the money spent on inventory items is focused on approximately 20 percent of the part numbers. This being true, you just might want to use a sophisticated forecast tool on the items that you spend the significant portion of your inventory dollars.

On the lower-volume inventory, where you spend fewer dollars, you could use a simpler and possibly better-suited forecast tool.

Mid-range inventory may fall into a category that could use a fairly complex forecast tool that could be cost effective for that inventory category.

And, when it comes to the critical and major items you have in your inventory, you are looking at a group of parts in inventory that cannot and should not be forecast.

For a fifth category, you have those parts in the system that have no predictable use pattern. For whatever reason, they must fall in the category of being unforecastable.

Doesn’t it make sense to use different forecast methods for different inventory class types? I believe it does.

But no matter what group of forecasting systems that you select, the one thing you must remember is that it is you who must enter costs, use patterns, use rates, safety stock levels, service levels, and all other historical and future use rates into the forecast system for it to work. This is not included in the software.

Forecasting programs are highly reliable and sophisticated for the things that they do. However, all they do is incorporate math on the numbers you enter into the program. 

What you will read in my upcoming MRO Coach inventory articles is how these forecast tools work and how to interpret the forecast that they make.

R.T. "Chris" Christensen is the director of the University of Wisconsin School of Business' operations management program. If you have an inventory management question, contact Coach Christensen by phone at or e-mail .

Back to top

Back to MRO Coach archives