What this calculator does
Safety stock is the extra inventory held above expected usage, sized to cover the ordinary swings in demand that happen even when nothing has gone wrong. It exists because average daily usage is exactly that, an average, and actual demand on any given day will sit above or below it.
The amount of buffer needed depends on how much demand actually varies day to day, how long the supplier takes to deliver, and how much risk of stocking out the business is willing to accept. A higher desired service level, meaning a lower tolerance for stockouts, calls for a bigger buffer, which is the trade-off this calculator makes explicit through the service-level setting.
The formula
Multiply a Z-score, drawn from the desired service level, by the standard deviation of daily demand, then by the square root of the lead time in days. The Z-score is a standard statistical value that widens the buffer as the target service level rises: 1.28 for 90%, 1.65 for 95%, 1.96 for 97.5%, and 2.33 for 99%.
| Term | Meaning |
|---|---|
| Safety stock | The buffer held above expected usage: Z × standard deviation of daily demand × √(lead time in days). |
| Standard deviation of daily demand | A measure of how much daily sales or usage typically varies from the average. |
| Lead time | The number of days between placing an order and receiving stock. |
| Service level | The chosen probability of not stocking out during lead time, which sets the Z-score used. |
The inputs explained
| Field | What to enter |
|---|---|
| Standard deviation of daily demand (units) | How much daily demand for this item typically varies, in units; a higher figure means more day-to-day swings. |
| Lead time (days) | The supplier lead time in days, the same figure used in the reorder point calculation. |
| Desired service level | The desired probability of not running out of stock during lead time; a higher service level needs more buffer stock. |
When to use it
Sizing buffer stock for a volatile item
An item with erratic day-to-day demand needs a larger safety stock than a steady seller with the same average usage, and this calculation captures that difference through the standard deviation input.
Choosing a service level for a critical product
A product that cannot be allowed to stock out, such as a best-seller or a component with no substitute, justifies a higher service level and therefore a larger buffer than a minor or easily substituted item.
Feeding safety stock into the reorder point
The figure calculated here plugs directly into the reorder point calculation as the buffer added on top of expected usage during lead time.
Worked examples
Every figure in the tables below is produced by this page’s own calculator at build time, so the numbers and the tool always agree. Select any row to load that scenario.
How safety stock changes with service level at a fixed demand variability and lead time
A fixed 5-unit standard deviation of daily demand and 14-day lead time, across the four standard service levels.
| Service level | Safety stock | Z-score used |
|---|---|---|
| 90% | 24 units | 1.28 (for 90% service level) |
| 95% | 31 units | 1.65 (for 95% service level) |
| 97.5% | 37 units | 1.96 (for 97.5% service level) |
| 99% | 44 units | 2.33 (for 99% service level) |
How safety stock changes with lead time at a fixed demand variability and service level
A fixed 5-unit standard deviation and 95% service level, across a range of lead times.
| Lead time | Safety stock |
|---|---|
| 7 days | 22 units |
| 14 days | 31 units |
| 21 days | 38 units |
| 28 days | 44 units |
| 35 days | 49 units |
| 42 days | 53 units |
Questions
Where do the Z-scores come from?
They are standard values from the normal distribution: the number of standard deviations needed to cover a given percentage of outcomes. A 95% service level, for example, corresponds to a Z-score of 1.65, meaning demand is expected to stay within that buffer 95% of the time.
How do I find the standard deviation of daily demand?
It is normally calculated from historical daily sales or usage figures for the item. Many inventory or point-of-sale systems report this directly; otherwise it can be computed from a run of past daily demand numbers.
Why does safety stock use the square root of lead time rather than lead time itself?
This reflects how variability accumulates over multiple days: uncertainty grows with the square root of the number of days, not linearly, which is the standard statistical treatment for demand that varies independently from day to day.
Is a 99% service level always the right choice?
Not necessarily. A higher service level ties up more cash in buffer stock that may sit unused most of the time. The right level depends on how costly a stockout would be for that particular item, weighed against the cost of holding the extra inventory.
This safety stock figure feeds directly into the inventory reorder point calculator, which combines it with expected usage during lead time.