Featured Video
This Week in Quality Digest Live
Quality Insider Features
Laurel Thoennes @ Quality Digest
‘It would be the first time we as scientists can put our hands on this problem of consciousness.’
Fran Webber
Tell NIST what they are, and your name could go down in history
Steven Brand
Classic tools for your organization
Scott Gottlieb
A plan for digital health devices
Bruce Hamilton
Square footage as a badge of success

More Features

Quality Insider News
It’s time that healthcare began to learn a long-term strategic approach to transformation
Leading scanner manufacturers involved in development of draft standard
New unit uses wireless and controller-free laser tracker technology
Drip irrigation targets the plant and not the soil
New approach uses light instead of electricity
Features faster measurement speed, onscreen averaging, and auto-rotating display
If you want to understand a system, try and change it
Components will be designed from the onset to inhabit multiple configurations during service

More News

Mark R. Hamel

Quality Insider

Calculating Average Daily Demand

Nine elements to consider about this deceptively complex concept

Published: Monday, July 18, 2011 - 15:04

Lean is largely about satisfying customer requirements. That’s nearly impossible if the lean practitioner doesn’t understand demand. In fact, misunderstand average daily demand, and the impact can be significant, including inaccurate takt times, improper demand segmentation, poorly sized kanban, and incorrect reorder points. Calculating average daily demand can be deceptively complex. Here are a handful of things to consider.

SKU and part number vs. product family.Kanban is applied at the SKU (stock-keeping unit) and part number level, so average daily demand must be calculated at that level as well. When calculating takt time, average daily demand is often, but not always, determined at the product family level, or at least the group of products or services that are produced or delivered within a given line, cell, or team.

True demand. Do not blindly accept what was sold, produced, processed, purchased, or issued as true historical demand. Often this demand can be:
• Capped by internal constraints, whether capacity- or execution-related, leaving unmet demand, which may or may not be fulfilled by competitors or may become back-ordered
• Artificially inflated due to overproduction, or purchasing of excess stock


If the barriers to constrained demand will be addressed in the near future, then include both historical met and unmet demand. In the area of overproduction or overpurchasing, identify the real demand and use it.

Historical vs. forecasted demand. If forecast demand is different than historical and the lean practitioner has faith in the forecast accuracy, then the forecast should be used to determine average daily demand (with historical most likely used to determine demand variation). Otherwise, use historical demand.

Abnormal historical demand. Historical demand, whether considered for the purpose of determining average daily demand or demand variation, may very well contain abnormal data. If they are significant and there is a reasonable probability that something of that nature and magnitude will not occur in the future (i.e., one-time order or marketing promotion), then it may be prudent to exclude those data from the analysis.

Demand horizon. Demand is rarely constant over extended periods of time. Narrowing the demand horizon will increase the risk of missing seasonality, cyclicality, and other significant variation. This is important for calculating both average daily demand and demand variation. The historical horizon often should be as much as 12 to 36 months, with forecast future horizon three to 18+ months. Statistically speaking, the practitioner needs ±25 data points to make valid calculations.

Demand time buckets. Clearly, the size of demand time buckets does not impact the purely mathematical calculation of average daily demand. However, the use of daily or weekly demand time buckets, as opposed to monthly or quarterly, does provide the necessary insight to visually identify abnormal demand and inflection points for seasonal demand changes. Furthermore, smaller buckets are required for calculating statistically valid demand variation (really, the coefficient of variation).

Number of operating days. “Average daily” presumes a denominator in days. The number of days must correspond to the number of operating days for the resource that is satisfying the demand. For kanban we have to remember that the resource is the “owner” of the supermarket.

Operating days without activity. Demand analysis will sometime reveal SKUs or parts that have days (or even weeks) that do not have any demand. This, by its nature, typically is indicative of relatively high demand variation. Depending upon the situation, the lean practitioner, when sizing kanban, may consciously want to include the zeros within the calculations or not (or not use kanban at all). For example, excluding zeros will drive a higher average daily demand and a lower coefficient of variation. The excluded zero approach will more likely ensure that the kanban can meet the spiked demand, but at a price: more inventory.

Any thoughts or war stories? 


About The Author

Mark R. Hamel’s picture

Mark R. Hamel

Mark R. Hamel is a lean Six Sigma implementation consultant and author. He is founder of GembaTales, a blog for providing insight into the application of certain lean concepts, and co-founder of the Lean Math blog—a tool and construct for thinking to integrate lean math theories with application. His book, Kaizen Event Fieldbook: Foundation, Framework, and Standard Work for Effective Events (Society of Manufacturing Engineers, 2010), received a Shingo Research and Professional Publications Award. Hamel can be reached at mark@kaizenfieldbook.com.