*In this series of blog posts, we have been talking about Jane who is in the role of inventory planner at her company. Kate, who is a consultant, has been helping Jane with the concepts.*

*The first ten parts of the blog are here: part 1, part 2, part 3, part 4, part 5, part 6, part 7, part 8, part 9, and part 10.*

Jane looked outside the window and said, “It is almost time to go home but I do have a question about what we discussed today. Are the three variance terms roughly equal in real life with real data?”

Kate replied, “Not really. Let us think this through. One easy way to think about it is that the demand is the most unpredictable as it is driven by outside forces, i.e., the customer. So, that should contribute the most to the uncertainty and therefore the safety stock. Also, the demand numbers are typically the biggest in the sense that you are shipping hundreds if not thousands or tens of thousands of units of demand any given day. Now, because we add up the variance of demand across days, the impact of these large numbers is very significant. When we look at the lead time, that variance needs to be added only once. And typically, the order quantity is more than the daily demand. So that variance also gets added only a few times. Plus, the suppliers typically have an incentive to supply exactly what you ordered, so they do try and keep the delta as small as possible. As a result, this variance comes out to be a relatively small number in most of the cases. I often see that the variance coming from demand is 60-80% of the total variance.”

Jane looked puzzled and asked, “So do you just add the variances up and calculate the percentage of each term against the total?”

Kate replied, “Indeed, if you think of the three terms simply as first, second and third, then here is what they are:”

Kate wrote on the whiteboard:

1^{st} variance term = Variance from demand

2^{nd} variance term = Variance from lead time

3^{rd} variance term = Variance from the supply quantity

Total Variance = 1^{st} variance term + 2^{nd} variance term + 3^{rd} variance term

1^{st} variance term as a % = 1^{st} variance term / Total Variance. And so on.

Kate continued, “If we look at the data you provided, and the three variance terms we calculated, we can see what the percentage contribution of each term is. Do you have the numbers?”

Jane created the following table on the whiteboard.

Kate said, “Since we have the numbers, let us go ahead and calculate the percentages.”

After some number crunching, Jane updated the table.

Kate was satisfied and said, “As you can see, fully 82% of the variance is coming from demand or the first term. That is way more significant than the other two terms combined. Very similar to what I see with my other customers.”

Jane nodded in agreement and said, “I have learned a lot today. Let us continue the conversation tomorrow.”

We will pick it up from there in our next blog.