Safety stock or buffer stock is a term used to describe the amount of inventory or stock other than pending orders or average demand that must be in place to reduce the chance of a temporary stock shortage or out of stock. Out of stock can result in lost sales and customers. Safe stock is useful for handling sharp increases in demand or ensuring the availability of raw materials and sufficient supply to keep production running while awaiting the next scheduled delivery of materials from suppliers. It is important to calculate it accurately, because too little stock will result in a shortage of inventory, while too much inventory will result in increased holding costs. The amount of safe stock depends on the service objective (i.e. how often you are allowed to run out of stock), the variability in demand, and the variability in the length of the order grace period.
Step
Method 1 of 3: Determining Safe Stock from Demand
Step 1. Study the demand record and its variability to determine how to avoid running out of stock
The following calculation will predict the stock required to reach a given level of service cycle, i.e. the percentage of supply cycles that could result in out of stock.
Step 2. Determine the average demand
Average demand is the total amount of material or goods needed each day during a certain period. A general approach is to check the total usage of a particular item over a certain period, for example a calendar month or the interval between ordering and delivering stock, then dividing by the number of days in the month to find usage per day. For many items, such as a well-known grocery store brand, past demand will provide the best guide for calculating demand.
Step 3. Consider future demand for the supply of a particular item
Sometimes it makes more sense to account for later requests. For example, if you manufacture car transmissions and receive a large order, enter that order as a demand factor. In this case, consider calculating the average demand and then adding it to the demand generated by the large order.
Step 4. Calculate demand variability
Average requests can provide so much information. If demand fluctuates dramatically from month to month or day to day, you'll need to factor that into your calculations too so that there's enough stock to deal with the surge in demand. Start by using a spreadsheet to calculate the standard deviation in the demand (in Excel, enter all the demand numbers in its own cell, then the formula is =STDEV(cell in question)). Or use the following formula:
- Start with the average demand over a given period (week, month, or year). For example, say 20 units per month.
- Determine the absolute difference between each data point and the average. For example, if the monthly demand is 8, 28, 13, 7, 15, 25, 17, 33, 40, 9, 11, and 34 units, then the absolute difference from 20 is: 12, 8, 7, 13, 5, 5, 3, 13, 20, 11, 9, and 14.
- Square each difference. In this example the squared results are: 144, 64, 49, 169, 25, 25, 9, 169, 400, 121, 81, and 196.
- Calculate the mean of the squares. For example. 121
- Calculate the mean square root. This is the standard deviation of demand. For example 11
Step 5. Determine the service factors, or Z values
The service factor, or Z value, is based on the standard deviation of demand. A Z value of 1 will protect you from the standard deviation of demand 1. For the example above, since the standard deviation of demand is 11, it takes 11 units of safe stock in addition to the normal stock to protect against one standard deviation, which results in a Z value of 1, 22 units of safe stock will produce a Z value of 2.
Step 6. Determine the Z value you are looking for
The higher the Z value, the less likely it is to run out of stock. In choosing a Z value, balance customer service and storage costs. You will want a higher Z-score with greater value to your business. A Z value of 1.65 will satisfy demand with a 95% confidence level, usually considered acceptable for even important stocks. In this case, that value means holding a stock of approximately 18 units (standard deviation for 11 x 1.65) of safe stock, or 38 units of total (average demand + safety stock). Here's how to relate the Z value to the probability of fulfilling the request:
- Z value 1 = 84%
- Z value 1.28 = 90%
- Z value 1.65 = 95%
- Z value 2, 33 = 99%
Method 2 of 3: Calculating Waiting Periods
Step 1. Factor in the waiting period for supply variability
The order lead time is the time from when you decide to manufacture or order an item until the item is on hand and ready to be sold to the final customer. There are several factors that affect the difference in waiting periods:
- Production delays - if your own production process varies, this could affect the lead time. In addition, the production process of the product you ordered can also vary.
- Material defects - If you order 10 units and there are 2 defective units, you will have to wait again for 2 units.
- Delivery delays - Delivery times can be expected to vary slightly under good conditions, whereas unforeseen events such as natural disasters or work strikes can delay deliveries even longer.
Step 2. Synchronize your stock with the supply delivery cycle
To synchronize, you must adjust the standard deviation of the request to match the waiting period. Multiply the standard deviation of demand (calculated in Section 1, Step 4) by the square root of the lead time.
- This means that if you calculate the standard deviation on a monthly basis, and the waiting period is 2 months, multiply the standard deviation by the square root of 2.
- Using the previous example, then: 11 x 2 = 15, 56.
- Be sure to convert the waiting period to the same unit of time that you used to calculate the standard deviation of the request. For example, if you calculate the standard deviation on a monthly basis and the waiting period is 10 days, convert the waiting period to 0.329 months - which is 10 divided by 30.42 (the average number of days in a month).
Step 3. Combine all
We can combine the formulas to determine safe stock on demand by calculating the waiting period factor as follows:
- Safety stock = Z value x waiting period x standard deviation of demand
- In this example, to 95% avoid stockout, you need 1.65 (Z-value) x 2 (lead time) x 11 (standard deviation of demand) = 25.67 units of safety stock.
Step 4. Calculate safety stock differently if lead time is the primary variable
If demand is constant but the lead time for orders varies, you should calculate safe stock using the lead time standard deviation. In this case the formula is:
- Safety stock = Z value x standard deviation of lead time x average demand
- For example, if you aim for a Z-value of 1.65, with constant average demand at 20 units per month, and the waiting period over a 6 month period is 2, 1, 5, 2, 3, 1, 9, 2, 1, and 2.8 months, then safety stock = 1.65 x 0.43 x 20 = 14, 3 units.
Step 5. Use the third formula to account for independent variations in lead times and demand
If the lead time and demand differ independently of each other (i.e. the factors that cause the difference differ from each other), then the safety stock is calculated by multiplying the Z value by the square root of the sum of the squares of demand and supply variability, or:
- Safety stock = Z value x [(waiting period x standard deviation of demand squared) + (standard deviation of waiting period squared x average demand squared)]
- In the example above: safety stock = 1.65 x [(2 x 11 squared) + (0.43 x 20)squared] = 29.3 units.
Step 6. Add up the calculations based on the variability of the waiting period and demand if the two factors vary independently
That is, if the same factors affect the variability of lead times and demand, you must add up the individual safe stock calculations to make sure you have enough safety stock yourself. In this case:
- Safe stock = (Z value x waiting period x demand standard deviation) + (Z value x waiting period standard deviation x average demand)
- In the example above: safety stock = 25, 67 + 14, 3 = 39, 97 units.
Method 3 of 3: Reducing the Need for Safe Stock
Step 1. Reduce the amount of safety stock needed to save money
Having too much stock on hand increases holding costs, so it is ideal to run a lean supply chain. Remember, the goal is not to prevent all out of stock events, but to balance customer service goals and storage costs.
Step 2. Monitor usage of safe stock
Is your model working as expected? If so, the use of safe stock should be half the supply cycle. If your safe stock usage is lower, perhaps the amount held can be reduced.
Step 3. Reduce demand variability
Demand tends to be more variable than lead times and has a greater impact on the safe stock formula. Smoothing out demand variability will allow you to hold less safety stock. Demand can be formed by adjusting prices, waiting periods, or the content of the product being produced.
Step 4. Strive to reduce waiting periods
If your lead time is zero, no safe stock is needed because products can be produced instantly if there is demand. Of course, waiting periods can never be reduced to zero, but the best way to run a leaner business is to keep the waiting period as low as possible. This means tightening supply chains and production processes.
Step 5. Change customer service targets
If there is no need to provide a high level of customer service, i.e. when out of stock will not result in the loss of a customer, you just need to adjust the Z value down to reduce the amount of safe stock that must be on hand.
Step 6. Implement a faster process
This process allows you to produce or deliver goods faster in order to prevent out of stock. As a result, your company will not be required to keep a lot of safe stock. This is useful if the cost of producing the stock of goods in question is high enough, causing more costs in storage.
Step 7. Consider changing the production process from Make to Order (MTO), i.e. the production of goods is only carried out if there is an order, to Finish to Order (FTO), i.e. the production components are already available and all you have to do is assemble according to the customer's order
If customers are willing to accept a longer waiting period, which is often the case with non-routine purchases of goods, MTO is an option that can eliminate most safe stock, whereas FTO allows less differentiation in safe stock versus keeping finished goods.
Tips
- There are several other methods for calculating safety stock, but all of them are based on using the standard deviation to determine demand variability and lead times. You can see some of the other formulas here.
- Make sure you understand the formula used and check to make sure it works properly. If your business is running for three to four months without dealing with safe stock, or vice versa if you experience two or more out of stock in a six month period, then you should reevaluate the amount of safe stock available.
