BIZOMAT Tools · Inventory
Safety Stock
How much buffer stock should you hold?
Sizes safety stock by the statistical service-level method when demand and lead-time variation are known, and by the max-minus-average rule otherwise.
Open the calculatorRuns in your browser. No account needed.
How this tool works
Inputs, units and where to find them
| Input | Unit | Typical source |
|---|---|---|
| Maximum daily demand | units/day | Highest normal daily demand in recent history |
| Maximum lead time | days | Longest normal lead time experienced |
| Average daily demand | units/day | Average daily demand |
| Average lead time | days | Average lead time in days |
| Std deviation of daily demand (0 = not known) | units/day | Standard deviation of daily demand from 6–12 months of history |
| Std deviation of lead time (0 = not known) | days | Standard deviation of lead time from receipt records |
| Target cycle service level | choice | Target probability of not stocking out in a replenishment cycle |
What each input means
Open an input to see what it is, its units, the worked example and the common mistakes, with a small diagram.
What this means: Maximum daily demand
- What it is
- The highest daily demand seen in normal trading over recent history, leaving out one-off events you would not plan for.
- Units and format
- Enter a number in units/day: units/day. The form accepts 0 units/day or more.
- Example
- The form opens with 60 units/day as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- In the max-minus-average method, a higher maximum raises safety stock.
- Get it right
- Used only by the max-minus-average method; once a standard deviation is entered, it appears only in the comparison table.
What this means: Maximum lead time
- What it is
- The longest normal lead time experienced from this supplier in recent history, from order to receipt.
- Units and format
- Enter a number in days: days. The form accepts 0 days or more.
- Example
- The form opens with 14 days as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- In the max-minus-average method, a longer maximum raises safety stock.
- Get it right
- Ignore rare extreme delays such as a one-off port strike, or the buffer becomes very large.
What this means: Average daily demand
- What it is
- The average number of units used per day over the same history as the maximum and the standard deviation.
- Units and format
- Enter a number in units/day: units/day. The form accepts 0 units/day or more.
- Example
- The form opens with 40 units/day as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Used in both methods; in the statistical one it scales the effect of lead-time variation.
- Get it right
- Use the same day basis (working or calendar) as the lead times.
What this means: Average lead time
- What it is
- The average time from order to receipt over recent orders from this supplier.
- Units and format
- Enter a number in days: days. The form accepts 0 days or more.
- Example
- The form opens with 9 days as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- In the statistical method, a longer average lead time exposes you to more demand variation.
- Get it right
- Measure it from receipt records rather than the supplier’s quoted lead time.
What this means: Std deviation of daily demand (0 = not known)
- What it is
- How much daily demand scatters around its average, measured as the standard deviation of daily demand over 6 to 12 months of history.
- Units and format
- Enter a number in units/day: units/day. The form accepts 0 units/day or more.
- Example
- The form opens with 0 units/day as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Statistical safety stock rises with this variation.
- Get it right
- 0 means not known. If both standard deviations are 0, the tool falls back to the max-minus-average method.
What this means: Std deviation of lead time (0 = not known)
- What it is
- How much the lead time scatters around its average, measured as the standard deviation of lead times from receipt records.
- Units and format
- Enter a number in days: days. The form accepts 0 days or more.
- Example
- The form opens with 0 days as a worked example. It is an illustration, not a recommended value: replace it with your own figure.
- Effect on the result
- Statistical safety stock rises with this variation, scaled by average daily demand.
- Get it right
- Enter it in days. 0 means not known; demand variation alone can still drive the statistical method.
What this means: Target cycle service level
- What it is
- The probability you want of not running out during one replenishment cycle. It sets the z value used by the statistical method.
- Units and format
- Choose one of 5 options from the list: 90 %; 95 %; 97.5 %; 99 %; 99.5 %.
- Example
- The form opens with “95 %” selected as a worked example. Choose the option that matches your case.
- Effect on the result
- A higher service level raises z and so the statistical safety stock, increasingly steeply.
- Get it right
- This is per cycle, not the fill rate. It has no effect unless a standard deviation is entered.
Method and formulas
- Statistical: SS = z × √(L × σd² + d² × σL²), with z from the service level (95% → 1.645)
- Rule of thumb: SS = max daily × max lead − average daily × average lead
Limitations
- The statistical method assumes independent, roughly normal demand
- Lumpy, seasonal or intermittent demand needs other methods
Typical uses
- Setting buffers for purchased and made items
- Reviewing service levels and stock-outs
Who it is for
- Inventory planners
- Supply chain analysts
What you get
- Safety stock in units and days
- Comparison of the two methods
Interpreting the result
- Higher service levels raise safety stock steeply above about 97.5%
- Without variation data, treat the result as a rule of thumb
References
- Silver E. A., Pyke D. F. and Thomas D. J., Inventory and Production Management in Supply Chains (CRC Press)
Learn the Concepts Behind This Tool
These BIZOMAT Library readings explain the method this tool uses, with worked examples.
Method explained here · Library collection
Demand forecasting for small manufacturers: matching supply with demand without drowning in stock
In Manufacturing Operations and Design for Manufacture
What it covers: Practical forecasting and planning for small manufacturers: simple forecasting methods, measuring forecast error, safety stock, reorder points, order quantities and a monthly planning meeting.
BIZOMAT tools are screening and decision-support utilities. Verify important financial, engineering, safety, legal or operational decisions using appropriate professional standards and your organisation’s approved data.