Main content

John R. Dougherty 

Inaccurate sales forecasts are the single most common problem shared by every company, large or small.  There are many techniques, approaches and tools for reducing forecast error – but none of them can ensure completely accurate forecasts.  So it is paramount for every company to develop mechanisms that will support good customer service, while controlling inventories and costs.  These mechanisms should be deployed selectively, depending on the type of forecast inaccuracy and the supply chain characteristics of the products.  

Two Types of Forecast Inaccuracy

Bias represents a consistent forecast error in the same direction (above or below forecast) over a period of time.  Often bias can be caused by undetected business cycles, or long-term trends.  Sometimes the bias is due to organizational or personal considerations such as always forecasting low so that sales and marketing can “beat the numbers.”  In other cases, forecasts are always high to justify new product introductions, capacity expansions and/or inventory availability; or to match an aggressive revenue growth target from top management; or to justify advertising, spending or staffing budgets.

It is critical to identify and adjust for these or any other causes of bias, since it will have the largest cumulative impact on costs, inventory, and customer service. 

“Random” or “normal” deviation above and below the average demand is the other portion of forecast error.  This “lack of linear demand pattern” is more prevalent in some products than others.  It is affected by the behaviors, practices, and economics of demand chain partners (customers, distributors, dealers, etc.) who affect the timing and quantity of the product being ordered.

For example, low volume, low cost products are much more likely to have non-linear demand since it is easier and more cost efficient for the demand chain customers to lot size or order the materials less often, without paying the price of a large investment in inventory.

Eliminating (Not Coping With) Bias

There must be a forecast monitoring and management process that analyzes variations over longer periods of time to differentiate between bias and “normal variation.”  Otherwise, just looking at last month’s sales could trigger adjustments of forecasts up and down in response to normal variations when, in fact, the average forecast is accurate and what is needed is the ability to accommodate these variations.  And undetected bias may not be noticed for several months, until inventories or backorders are excessively high.

Bias is often most easily visible in aggregate, at the S&OP level month after month after month – where strong executive leadership can step in to question it and insist that it be corrected. 

Often there is a temptation to cope with bias by immediately increasing or decreasing the supply plans.  This is dangerous and almost always ineffective, since it ignores the cause of the bias, and then can’t stay calibrated to the changing impact of the bias.  And it causes confusion and diminishes accountability for maintaining clearly reconciled demand and supply plans.  

The process should also provide the forum for identifying gaps between current estimated sales vs. the budgeted revenue plans, since often the source of bias is pressure to achieve financial results or at least to give the perception that the financial targets will be met. The forecasting process must be truthful so that gaps are visible and lead to adjustments to bring reality and expectation into alignment.  This can sometimes be done via activities in the sales and marketing organizations (and with demand chain partners) to alter demand patterns, offset market forces, or change activities to get future demand patterns back on track to meet business plans.  This is sometimes called “demand shaping”.  Where this is not possible or practical, budgets, financial plans, and other targets for the rest of the organization must be adjusted, to insure that the effect of these situations are dealt with optimally.

The responsible sales and marketing management must play a major role, as well as forecast analysts, demand managers and planners. When bias is detected, and the actual demand patterns cannot be altered, the forecasts should be adjusted up or down over the planning horizon.  This then will trigger adjustments in family supply or production plans, and master schedules, maintaining transparent and reconciled demand and supply plans. 

Either way, the bias is eliminated, not merely coped with.  The mechanism:  a proactive, monthly forecasting process, tightly integrated with sales and marketing activities, supply planning, and master scheduling, all regularly monitored by senior management through the S&OP process!

Coping With “ Normal ” Deviation

Once bias is dealt with, attention should be paid to those annoying “up’s and down’s” that can’t be avoided.  How?  Plan for the variation.  There are a wide variety of techniques to help, including:

·         Moving to finish-to-order or make-to-order production approaches, so as to not commit material and capacity resources until the true customer requirements are known.

·         Shortening supply chain lead times to minimize the early commitment of inventories, and facilitate the adjustment of schedules to actual customer demands as received.  For off-shore suppliers this may require smaller, more frequent deliveries.

·         Increase manufacturing flexibility to more easily enable short-term schedule changes to respond to shifts in demand from the customers.

·         Planning for safety capacity to allow variation in demands to be accommodated by changes to the schedule, whether in total volume or in mix, or between one manufacturing area and another.

·         Selective “overplanning”, which reserves capacity and plans for materials to be available to respond to near-term shifts in demand, both within the manufacturing facility and for all critical supply chain partners.

·         Safety stock, at finished goods, intermediate, and / or raw material levels, to optimize flexibility to respond to demand shifts while minimizing inventory investment.  The shorter the lead times, and the more flexible the manufacturing process, the easier it will be to hold the inventories earlier in the cycle (raw materials or at the suppliers), thus keeping it in its most flexible form, not having committed it to any particular form or use until absolutely necessary.

·         Involve all supply chain and demand chain partners in the planning process to deal with the impact that variation has on them.  Ensure that integrated, non-redundant strategies are implemented as to where and how much inventory or capacity should be held or planned for, to accommodate the expected variation.   

Forecasting is an old problem made worse by the dynamic business environment of today.  The solution isn’t just new and improved “advanced forecasting” software tools.  It requires more enlightened and selective use of a variety of traditional approaches developed over the last 50 years. With a clear understanding of the causes of variation, techniques to eliminate or accommodate the variation should be implemented based on sharing information, and better integrating and aligning data and business practice across all demand and supply chain partners. 

John R. Dougherty is a founding Senior Partner of Partners for Excellence (, a 31 year consultant and educator, and the co-author of Sales & Operations Planning Best Practices.  He can be contacted @ 978-375-7808 or This email address is being protected from spambots. You need JavaScript enabled to view it..


If you have specific questions about this article or want to discuss it with the author, call John Dougherty at 1 978-375-7808.

The Partners for Excellence specialize in helping companies set up comprehensive measurement programs and improving overall resource management performance.  Contact us at 1 978-375-7808 or email This email address is being protected from spambots. You need JavaScript enabled to view it..