How do you calculate safety stock?

Multiply your service factor (z) by the daily demand standard deviation, then by the square root of lead time in days. With z=1.65, sigma=36 and 12 days, that is 1.65 x 36 x 3.46 = about 206 units.

What service factor should I use?

The z value maps to your target cycle service level: 1.28 for 90%, 1.65 for 95%, 2.05 for 98% and 2.33 for 99%. Higher service means more buffer, so reserve high z values for A-class or line-critical parts.

What is lead-time demand and how is it different from safety stock?

Lead-time demand is the average quantity you expect to consume during the lead time (180 x 12 = 2,160 units here). Safety stock sits on top of that to cover variability. Your reorder point is the sum of both, 2,366 units in this example.

Why does safety stock scale with the square root of lead time, not lead time itself?

Demand variation over multiple days partially averages out, so risk grows with the square root of time rather than linearly. Doubling lead time raises safety stock by about 1.41x, not 2x.

What is a good safety stock level?

There is no universal number; it should give you the service level the business wants at the lowest reasonable cost. A useful check is buffer days: here 206 units equals only about 1.1 days of average demand, which is a lean, defensible cushion for a 95% target.

How often should I recalculate safety stock?

Refresh the demand standard deviation and lead time at least quarterly, and after any seasonality shift, supplier change, or demand-pattern break. Stale sigma values are the most common reason buffers drift out of line with reality.

Planning calculator

Safety Stock Calculator

Safety stock is the buffer inventory you hold to absorb demand and lead-time variability so a stockout does not happen between replenishment cycles. Planners, buyers and S&OP teams size it directly into reorder points and min/max settings in the ERP. Carry too little and you risk line-down events or backorders; carry too much and you tie up working capital and warehouse space. The statistical formula links your target service level to the demand variation you actually see, so the number is defensible rather than a gut-feel pad.

What this calculator does

Estimate buffer stock from demand variation, lead time, and a service factor.
Use when setting inventory buffers for purchased or manufactured parts with variable demand.
It computes the units of buffer stock needed to hit a chosen service level given daily demand variability over the replenishment lead time.

Formula used

Safety stock = service factor × demand standard deviation × √lead time
Lead-time demand = average daily demand × lead time
Protected quantity = lead-time demand + safety stock

Inputs explained

Average daily demand: undefined
Daily demand standard deviation: undefined
Lead time: undefined
Service factor: undefined

How to use the result

Use it when setting reorder points, min/max levels, or kanban buffer sizes for items with variable demand and a known, reasonably stable lead time.
The square-root-of-lead-time model assumes lead time is fixed; if supplier lead time itself swings widely, this understates the buffer and you should use the combined demand-and-lead-time variance form instead.

Current U.S. benchmarks

U.S. manufacturing runs at 75.6% of capacity (Federal Reserve, May 2026). New factory orders are up 2.3% year over year (Census).

Common questions

How do you calculate safety stock? Multiply your service factor (z) by the daily demand standard deviation, then by the square root of lead time in days. With z=1.65, sigma=36 and 12 days, that is 1.65 x 36 x 3.46 = about 206 units.
What service factor should I use? The z value maps to your target cycle service level: 1.28 for 90%, 1.65 for 95%, 2.05 for 98% and 2.33 for 99%. Higher service means more buffer, so reserve high z values for A-class or line-critical parts.
What is lead-time demand and how is it different from safety stock? Lead-time demand is the average quantity you expect to consume during the lead time (180 x 12 = 2,160 units here). Safety stock sits on top of that to cover variability. Your reorder point is the sum of both, 2,366 units in this example.
Why does safety stock scale with the square root of lead time, not lead time itself? Demand variation over multiple days partially averages out, so risk grows with the square root of time rather than linearly. Doubling lead time raises safety stock by about 1.41x, not 2x.
What is a good safety stock level? There is no universal number; it should give you the service level the business wants at the lowest reasonable cost. A useful check is buffer days: here 206 units equals only about 1.1 days of average demand, which is a lean, defensible cushion for a 95% target.

Last reviewed 2026-05-12.