True or false: The forecast doesn’t matter to spare parts inventory management.

At first glance, this statement seems obviously false. After all, forecasts are crucial for planning stock levels, right?

It depends on what you mean by a “forecast”. If you mean an old-school single-number forecast (“demand for item CX218b will be 3 units next week and 6 units the week after”), then no. If you broaden the meaning of forecast to include a probability distribution taking account of uncertainties in both demand and supply, then yes.

The key reality is that many items, especially spare and service parts, have unpredictable, intermittent demand. (Supplier lead times can also be erratic, especially when parts are sourced from a backlogged OEM.)  We have observed that while manufacturers and distributors typically experience intermittent demand on just 20% or more of their items the percentage grows to 80%+ for MRO based businesses.  This means historical data often show periods of zero demand interspersed with random periods of non-zero demand. Sometimes, these non-zero demands are as low as 1 or 2 units, while at other times, they unexpectedly spike to quantities several times larger than their average.

This isn’t like the kind of data usually faced by your peer “demand planners” in retail, consumer products, and food and beverage. Those folks usually deal with larger quantities having proportionately less randomness. And they can surf on prediction-enhancing features like trends and stable seasonal patterns. Instead, spare parts usage is much more random, throwing a monkey wrench into the planning process, even in the minority of cases in which there are detectable seasonal variations.

In the realm of intermittent demand, the best forecast available will significantly deviate from the actual demand. Unlike consumer products with medium to high volume and frequency, a service part’s forecast can miss the mark by hundreds of percentage points. A forecast of one or two units, on average, will always miss when the actual demand is zero. Even with advanced business intelligence or machine learning algorithms, the error in forecasting the non-zero demands will still be substantial.

Perhaps because of the difficulty of statistical forecasting in the inventory domain, inventory planning in practice often relies on intuition and planner knowledge. Unfortunately, this approach doesn’t scale across tens of thousands of parts. Intuition just cannot cope with the full range of demand and lead time possibilities, let alone accurately estimate the  probability of each possible scenario. Even if your company has one or two exceptional intuitive forecasters, personnel retirements and product line reorganizations mean that intuitive forecasting can’t be relied on going forward.

The solution lies in shifting focus from traditional forecasts to predicting probabilities for each potential demand and lead time scenario. This shift transforms the conversation from an unrealistic “one number plan” to a range of numbers with associated probabilities. By predicting probabilities for each demand and lead time possibility, you can better align stock levels with the risk tolerance for each group of parts.

Software that generates demand and lead time scenarios, repeating this process tens of thousands of times, can accurately simulate how current stocking policies will perform against these policies. If the performance in the simulation falls short and you are predicted to stock out more often than you are comfortable with or you are left with excess inventory, conducting what-if scenarios allows adjustments to policies. You can then predict how these revised policies will fare against random demands and lead times. You can conduct this process iteratively and refine it with each new what-if scenario or lean on system prescribed policies that optimally strike a balance between risk and costs.

So, if you are planning service and spare parts inventories, stop worrying about predicting demand the way traditional retail and CPG demand planners do it. Focus instead on how your stocking policies will withstand the randomness of the future, adjusting them based on your risk tolerance. To do this, you’ll need the right set of decision support software, and this is how Smart Software can help.

For too many companies, a critical piece of data fact-finding ― the measurement of demand uncertainty ― is handled by simple but inaccurate rules of thumb.  For example, demand planners will often compute safety stock by a user-defined multiple of the forecast or historical average.  Or they may configure their ERP to order more when on hand inventory gets to 2 x the average demand over the lead time for important items and 1.5 x for less important ones. This is a huge mistake with costly consequences.

The choice of multiple ends up being a guessing game.  This is because no human being can compute exactly how much inventory to stock considering all the uncertainties.  Multiples of the average lead time demand are simple to use but you can never know whether the multiple used is too large or too small until it is too late.  And once you know, all the information has changed, so you must guess again and then wait and see how the latest guess turns out.  With each new day, you have new demand, new details on lead times, and the costs may have changed.  Yesterday’s guess, no more matter how educated is no longer relevant today.  Proper inventory planning should be void of inventory and forecast guesswork.  Decisions must be made with incomplete information but guessing is not the way to go.

Knowing how much to buffer requires a fact-based statistical analysis that can accurately answer questions such as:

• How much extra stock is needed to improve service levels by 5%
• What the hit to on-time delivery will be if inventory is reduced by 5%
• What service level target is most profitable.
• How will the stockout risk be impacted by the random lead times we face.

Intuition can’t answer these questions, doesn’t scale across thousands of parts, and is often wrong.  Data, probability math and modern software are much more effective. Winging it is not the path to sustained excellence.

Do MRO companies genuinely prioritize reducing excess spare parts inventory? From an organizational standpoint, our experience suggests not necessarily. Boardroom discussions typically revolve around expanding fleets, acquiring new customers, meeting service level agreements (SLAs), modernizing infrastructure, and maximizing uptime. In industries where assets supported by spare parts cost hundreds of millions or generate significant revenue (e.g., mining or oil & gas), the value of the inventory just doesn’t raise any eyebrows, and organizations tend to overlook massive amounts of excessive inventory.

Consider a public transit agency.  In most major cities, the annual operating budgets will exceed $3 billion.  Capital expenses for trains, subway cars, and infrastructure may reach hundreds of millions annually. Consequently, a spare parts inventory valued at $150 million might not grab the attention of the CFO or general manager, as it represents a small percentage of the balance sheet.  Moreover, in MRO-based industries, many parts need to support equipment fleets for a decade or more, making additional stock a necessary asset. In some sectors like utilities, holding extra stock can even be incentivized to ensure that equipment is kept in a state of good repair.

We have seen concerns about excess stock arise when warehouse space is limited. I recall, early in my career, witnessing a public transit agency’s rail yard filled with rusted axles valued at over $100,000 each.  I was told the axles were forced to be exposed to the elements due to insufficient warehouse space. The opportunity cost associated with the space consumed by extra stock becomes a consideration when warehouse capacity is exhausted. The primary consideration that trumps all other decisions is how the stock ensures high service levels for internal and external customers.  Inventory planners worry far more about blowback from stockouts than they do from overbuying.  When a missing part leads to an SLA breach or downed production line, resulting in millions in penalties and unrecoverable production output, it is understandable.

Asset-intensive companies are missing one giant point. That is, the extra stock doesn’t insulate against stockouts; it contributes to them. The more excess you have, the lower your overall service level because the cash needed to purchase parts is finite, and cash spent on excess stock means there isn’t cash available for the parts that need it.  Even publicly funded MRO businesses, like utilities and transit agencies, acknowledge the need to optimize spending, now more than ever.  As one materials manager shared, “We can no longer fix problems with bags of cash from Washington.”  So, they must do more with less, ensuring optimal allocation across the tens of thousands of parts they manage.

This is where state-of-the-art inventory optimization software comes in, predicting the required inventory for targeted service levels, identifying when stock levels yield negative returns, and recommending reallocations for improved overall service levels.  Smart Software has helped asset intensive MRO based businesses optimize reorder levels across each part for decades. Give us a call to learn more. 

Balancing Act

Managing inventory, like managing anything, involves balancing competing priorities. Do you want a lean inventory? Yes! Do you want to be able to say “It’s in stock” when a customer wants to buy something? Yes!

But can you have it both ways? Only to a degree. If you lean into leaning your inventory too aggressively, you risk stockouts. If you stamp out stockouts, you create inventory bloat. You are forced to find a satisfactory balance between the two competing goals of lean inventory and high item availability.

Striking a Balance

How do you strike that balance? Too many inventory planners “guestimate” their way to some kind of answer. Or they work out a smart answer once and hope that it has a distant sell-by date and keep using it while they focus on other problems. Unfortunately, shifts in demand and/or changes in supplier performance and/or shifts in your own company’s priorities will obsolete old inventory plans and put you right back where you started.

It is inevitable that every plan has a shelf life and has to be updated. However, it is definitely not best practice to replace one guess with another. Instead, each planning cycle should exploit modern supply chain software to replace guesswork with fact-based analysis using probability math.

Know Thyself

The one thing that software cannot do is compute a best answer without knowing your priorities. How much do you prioritize lean inventory over item availability? Software will predict the levels of inventory and availability caused by any decisions you make about how to manage each item in your inventory, but only you can decide whether any given set of key performance indicators is consistent with what you want.

Knowing what you want in a general sense is easy: you want it all. But knowing what you prefer when comparing specific scenarios is more difficult. It helps to be able to see a range of realizable possibilities and mull over which seems best when they are laid out side by side.

See What’s Next

Supply chain software can give you a view of the tradeoff curve. You know in general that lean inventory and high item availability trade off against each other, but seeing item-specific tradeoff curves sharpens your focus.

Why is there a curve? Because you have choices about how to manage each item. For instance, if you check inventory status continuously, what values will you assign to the Min and Max values that govern when to order replenishments and how much to order. The tradeoff curve arises because choosing different Min and Max values leads to different levels of on hand inventory and different levels of item availability, e.g., as measured by fill rate.

A Scenario for Analysis

To illustrate these ideas, I used a digital twin  to estimate how various values of Min and Max would perform in a particular scenario. The scenario focused on a notional spare part with purely random demand having a moderately high level of intermittency (37% of days having zero demand). Replenishment lead times were a coin flip between 7 and 14 days. The Min and Max values were systematically varied: Min from 20 to 40 units, Max from Min+1 units to 2xMin units. Each (Min,Max) pair was simulated for 365 days of operation a total of 1,000 times, then the results averaged to estimate both the average number of on hand units and the fill rate, i.e., percentage of daily demands that were satisfied immediately from stock. If stock was not available, it was backordered.

Results

The experiment produced two types of results:

• Plots showing the relationship between Min and Max values and two key performance indicators: Fill rate and average units on hand.
• A tradeoff curve showing how the fill rate and units on hand trade off against each other.

Figure 1 plots on hand inventory as a function of the values of Min and Max. The experiment yielded on hand levels ranging from near 0 to about 40 units.  In general, keeping Min constant and increasing Max results in more units on hand. The relationship with Min is more complex: keeping Max constant,  increasing Min first adds to inventory but at some point reduces it.

Figure 2 plots fill rate as a function of the values of Min and Max.  The experiment yielded fill rate levels ranging from near 0% to 100%.  In general, the functional relationships between the fill rate and the values of Min and Max mirrored those in Figure1.

Figure 3 makes the key point, showing how varying Min and Max produces a perverse pairing of the key performance indicators. Generally speaking, the values of Min and Max that maximize item availability (fill rate)  are the same values that maximize inventory cost (average units on hand). This general pattern is represented by the blue curve. The experiments also produced some offshoots from the blue curve that are associated with poor choices of Min and Max, in the sense that other choices dominate them by producing the same fill rate with lower inventory.

Conclusions

Figure 3 makes clear that your choice of how to manage an inventory item forces you to trade off inventory cost and item availability. You can avoid some inefficient combinations of Min and Max values, but you cannot escape the tradeoff.

The good side of this reality is that you do not have to guess what will happen if you change your current values of Min and Max to something else. The software will tell you what that move will buy you and what it will cost you. You can take off your Guestimator hat and do your thing with confidence.

Figure 1 On Hand Inventory as a function of Min and Max values

Figure 2 Fill Rate as a function of Min and Max values

Figure 3 Tradeoff curve between Fill Rate and On Hand Inventory

Measuring the accuracy of forecasts is an undeniably important part of the demand planning process. This forecasting scorecard could be built based on one of two contrasting viewpoints for computing metrics. The error viewpoint asks, “how far was the forecast from the actual?” The accuracy viewpoint asks, “how close was the forecast to the actual?” Both are valid, but error metrics provide more information.

Accuracy is represented as a percentage between zero and 100, while error percentages start at zero but have no upper limit. Reports of MAPE (mean absolute percent error) or other error metrics can be titled “forecast accuracy” reports, which blurs the distinction.  So, you may want to know how to convert from the error viewpoint to the accuracy viewpoint that your company espouses.  This blog describes how with some examples.

Accuracy metrics are computed such that when the actual equals the forecast then the accuracy is 100% and when the forecast is either double or half of the actual, then accuracy is 0%. Reports that compare the forecast to the actual often include the following:

• The Actual
• The Forecast
• Unit Error = Forecast – Actual
• Absolute Error = Absolute Value of Unit Error
• Absolute % Error = Abs Error / Actual, as a %
• Accuracy % = 100% – Absolute % Error

Look at a couple examples that illustrate the difference in the approaches. Say the Actual = 8 and the forecast is 10.

Unit Error is 10 – 8 = 2

Absolute % Error = 2 / 8, as a % = 0.25 * 100 = 25%

Accuracy = 100% – 25% = 75%.

Now let’s say the actual is 8 and the forecast is 24.

Unit Error is 24– 8 = 16

Absolute % Error = 16 / 8 as a % = 2 * 100 = 200%

Accuracy = 100% – 200% = negative is set to 0%.

In the first example, accuracy measurements provide the same information as error measurements since the forecast and actual are already relatively close. But when the error is more than double the actual, accuracy measurements bottom out at zero. It does correctly indicate the forecast was not at all accurate. But the second example is more accurate than a third, where the actual is 8 and the forecast is 200. That’s a distinction a 0 to 100% range of accuracy doesn’t register. In this final example:

Unit Error is 200 – 8 = 192

Absolute % Error = 192 / 8, as a % = 24 * 100 = 2,400%

Accuracy = 100% – 2,400% = negative is set to 0%.

Error metrics continue to provide information on how far the forecast is from the actual and arguably better represent forecast accuracy.

We encourage adopting the error viewpoint. You simply hope for a small error percentage to indicate the forecast was not far from the actual, instead of hoping for a large accuracy percentage to indicate the forecast was close to the actual.  This shift in mindset offers the same insights while eliminating distortions.