The Correct Safety Stock Level is not Simple. Part 2.

In the past year, 25% of the search-term visits to our TopDown Lean Systems website have involved the words simple and/or Excel, in addition to safety stock. Supply Chain and IM professionals are looking for a better, easier safety-stock tool. The word simple suggests that ease of use (in Excel) is more important than precision, so long as the result is close enough. Can a safety-stock calculation be both simple also close enough?

Or as Albert Einstein said, “Make everything as simple as possible, but not simpler.”

How would we know if a safety-stock calculation is simple enough, but not simplistic, or too simple? In a previous blog, we acknowledged that most common safety stock calculations attempt to address these obvious factors:

• Target service level
• Lead time
• Demand variation
• Lead-time variation

In that previous blog, we also discussed how safety-stock formulas may cause your inventory levels to be excessive because of the z factor in those formulas: The z factor is simple, but it is not reliably close enough.

Now, let’s consider another factor that can affect safety stock: Replenishment interval, or RI.

RI is not the same as lead time, and if the two are the same, it’s coincidence. Common sense says that a short RI means small, frequent receipts, requiring less safety stock. Likewise, we know intuitively that a long RI means infrequent but large-quantity receipts, also requiring less safety stock. (Safety stock is at its highest when RI = lead time.)

The question is – how much less safety stock? What’s the mathematical relationship between RI and safety stock? Well, the short answer is that this relationship is not simple. But can we get close enough while excluding the complexities of RI from a simple safety-stock calculation?

Let’s look at an example:

Item 123 is high-volume, with demand virtually every day. It is also received almost every day, so its RI is only 1.1 days, in comparison to a 28-day lead time.

• Mean daily demand = 99000
• Demand standard deviation = 56000
• Mean lead time = 28 days
• Lead time standard deviation = 5.7
• Target OTD fill rate = 99%
• Z factor for 99% = 2.326, Excel NORMSINV(.99)
• Average RI = 1.1 days.

Excel safety-stock formula = 2.326 * SQRT ((28 * 56000^2) + (99000^2 * 5.7^2)) = 1,482,787

Is this safety stock of 1,482,787 units close enough?

Short Answer – NO.

The correct safety stock level is only 823,222 – a difference of 660,000 units, or 44% less!

Why is the simple safety-stock formula so far off?

  1. It is not a fill-rate formula, so it tends to provide a safety-stock level that’s higher than what we need for our OTD measurement.
  2. It does not accommodate the fact that this item is received virtually every day, and doesn’t need as much safety stock.

Clearly, the safety-stock formula is too simple, and its results are financially risky and sub-optimal. Can we adjust the formula for OTD and for RI? Yes, but when we do this correctly, the formula is anything but simple. And it still isn’t correct, for reasons we will discuss in blog posts to follow.

Are you looking for a correct way to set safety stock, so that you achieve your service-level targets without unnecessary inventory?

Nothing could be simpler than sending us your data, and we will send you your correct, comprehensive and optimal safety-stock levels. Contact us for more info on how simple we can help make it for you!