Sometimes a statistical forecast just doesn’t make sense.  Every forecaster has been there.  They may double-check that the data was input correctly or review the model settings but are still left scratching their head over why the forecast looks very unlike the demand history.   When the occasional forecast doesn’t make sense, it can erode confidence in the entire statistical forecasting process.

This blog will help a layman understand what the Smart statistical models are and how they are chosen automatically.  It will address how that choice sometimes fails, how you can know if it did, and what you can do to ensure that the forecasts can always be justified.  It’s important to know to expect, and how to catch the exceptions so you can rely on your forecasting system.

How methods are chosen automatically

The criteria to automatically choose one statistical method out of a set is based on which method came closest to correctly predicting held-out history.  Earlier history is passed to each method and the result is compared to actuals to find the one that came closest overall.  That automatically chosen method is then fed all the history to produce the forecast. Check out this blog to learn more about the model selection https://smartcorp.com/uncategorized/statistical-forecasting-how-automatic-method-selection-works/

For most time series, this process can capture trends, seasonality, and average volume accurately. But sometimes a chosen method comes mathematically closest to predicting the held-out history but doesn’t project it forward in a way that makes sense.  That means the system selected method isn’t best and for some “hard to forecast”

Hard to forecast items

Hard to forecast items may have large, unpredictable spikes in demand, or typically no demand but random irregular blips, or unusual recent activity.  Noise in the data sometimes randomly wanders up or down, and the automated best-pick method might forecast a runaway trend or a grind into zero.  It will do worse than common sense and in a small percentage of any reasonably varied group of items.  So, you will need to identify these cases and respond by overriding the forecast or changing the forecast inputs.

How to find the exceptions

Best practice is to filter or sort the forecasted items to identify those where the sum of the forecast over the next year is significantly different than the corresponding history last year.  The forecast sum may be much lower than the history or vice versa.  Use supplied metrics to identify these items; then you can choose to apply overrides to the forecast or modify the forecast settings.

How to fix the exceptions

Often when the forecast seems odd, an averaging method, like Single Exponential Smoothing or even a simple average using Freestyle, will produce a more reasonable forecast.  If trend is possibly valid, you can remove only seasonal methods to avoid a falsely seasonal result.  Or do the opposite and use only seasonal methods if seasonality is expected but wasn’t projected in the default forecast.  You can use the what-if features to create any number of forecasts, evaluate & compare, and continue to fine tune the settings until you are comfortable with the forecast.

Cleaning the history, with or without changing the automatic method selection, is also effective at producing reasonable forecasts. You can embed forecast parameters to reduce the amount of history used to forecast those items or the number of periods passed into the algorithm so earlier, outdated history is no longer considered.  You can edit spikes or drops in the demand history that are known anomalies so they don’t influence the outcome.  You can also work with the Smart team to implement automatic outlier detection and removal so that data prior to being forecasted is already cleansed of these anomalies.

If the demand is truly intermittent, it is going to be nearly impossible to forecast “accurately” per period. If a level-loading average is not acceptable, handling the item by setting inventory policy with a lead time forecast can be effective.  Alternatively, you may choose to use “same as last year” models which while not prone to accuracy will be generally accepted by the business given the alternatives forecasts.

Finally, if the item was introduced so recently that the algorithms do not have enough input to accurately forecast, a simple average or manual forecast may be best.  You can identify new items by filtering on the number of historical periods.

Manual selection of methods

Once you have identified rows where the forecast doesn’t make sense to the human eye, you can choose a smaller subset of all methods to allow into the forecast run and compare to history.  Smart will allow you to use a restricted set of methods just for one forecast run or embed the restricted set to use for all forecast runs going forward. Different methods will project the history into the future in different ways.  Having a sense of how each works will help you choose which to allow.

Rely on your forecasting tool

The more you use Smart period over period to embed your decisions about how to forecast and what historical data to consider, the less often you will face exceptions as described in this blog.  Entering forecast parameters is a manageable task when starting with critical or high impact items.  Even if you don’t embed any manual decisions on forecast methods, the forecast re-runs every period with new data. So, an item with an odd result today can become easily forecastable in time.

When managing service parts, you don’t know what will break and when because part failures are random and sudden. As a result, demand patterns are most often extremely intermittent and lack significant trend or seasonal structure. The number of part-by-location combinations is often in the hundreds of thousands, so it’s not feasible to manually review demand for individual parts. Nevertheless, it is much more straightforward to implement a planning and forecasting system to support spare parts planning than you might think.

This conclusion is informed by hundreds of software implementations we’ve directed over the years. Customers managing spare parts and service parts (the latter for internal consumption/MRO), and to a lesser degree aftermarket parts (for resale to installed bases), have consistently implemented our parts planning software faster than their peers in manufacturing and distribution.

The primary reason is the role in manufacturing and distribution of business knowledge about what might happen in the future. In a traditional B2B manufacturing and distribution environment, there are customers and sales and marketing teams selling to those customers. There are sales goals, revenue expectations, and budgets. This means there is a lot of business knowledge about what will be purchased, what will be promoted, whose opinions need to be accounted for. A complex planning loop is required. In contrast, when managing spare parts, you have a maintenance team that fixes equipment when it breaks. Though there are often maintenance schedules for guidance, what is needed beyond a standard list of consumable parts is often unknown until a maintenance person is on-site. In other words, there just isn’t the same sort of business knowledge available to parts planners when making stocking decisions.

Yes, that is a disadvantage, but it also has an upside: there is no need to produce a period-by-period consensus demand forecast with all the work that requires. When planning spare parts, you can usually skip many steps required for a typical manufacturer, distributor, or retailer. These skippable steps include:  

1. Building forecasts at different levels of the business, such as product family or region.
2. Sharing the demand forecast with sales, marketing, and customers.
3. Reviewing forecast overrides from sales, marketing, and customers.
4. Agreeing on a consensus forecast that combines statistics and business knowledge.
5. Measuring “forecast value add” to determine if overrides make the forecast more accurate.
6. Adjusting the demand forecast for known future promotions.
7. Accounting for cannibalization (i.e., if I sell more of product A, I’ll sell less of product B).

Freed from a consensus-building process, spare parts planners and inventory managers can rely directly on their software to predict usage and the required stocking policies. If they have access to a field-proven solution that addresses intermittent demand, they can quickly “go live” with more accurate demand forecasts and estimates of reorder points, safety stocks, and order suggestions.  Their attention can be focused on getting accurate usage and supplier lead time data. The “political” part of the job can be limited to obtaining organization consensus on service level targets and inventory budgets.

​

“Regardless of how much effort is poured into training forecasters and developing elaborate forecast support systems, decision-makers will either modify or discard the predictions if they do not trust them.”  — Dilek Onkal, International Journal of Forecasting 38:3 (July-September 2022), p.802.

The words quoted above grabbed my attention and prompted this post. Those of a geekly persuasion, like your blogger, are inclined to think of forecasting as a statistical problem. While that is obviously true, those of a certain age, like your blogger, understand that forecasting is also a social activity and therefore has a large human component.

What Do You Trust?

There is a related dimension of trust: not who do you trust but what do you trust? By this, I mean both data and software.

Trust in Data

Trust in data underpins trust in the forecaster using the data. Most of our customers have their data in an ERP system. This data must be understood as a key corporate asset. For the data to be trustworthy, it must have the “three C’s”, i.e., it must be correct, complete, and current.

Correctness is obviously fundamental. We once had a customer who was implementing a new, strong forecasting process, but found the results completely at odds with their sense of what was happening in the business. It turned out that several of their data streams were incorrect by a factor of two, which is a huge error. Of course, this set back the implementation process until they could identify and correct all the gross errors in their demand data.

There is a less obvious point to be made about correctness. That is, data are random, so what you see now is not likely to be what you see next. Planning production based on the assumption that next week’s demand will be exactly the same as this week’s demand is clearly foolish, but classical formula-based forecasting models like the exponential smoothing mentioned above will project the same number throughout the forecast horizon. This is where scenario-based planning is essential for coping with the inevitable fluctuations in key variables such as customers’ demands and suppliers’ replenishment lead times.

Completeness is the second requirement for data to be trusted. Our software ultimately gets much of its value from exposing the links between operational decisions (e.g., selecting the reorder points governing replenishment of stock) and business-related metrics like inventory costs. Yet often implementation of forecasting software is delayed because item demand information is available someplace, but holding, ordering and/or shortage costs are not.  Or, to cite another recent example, a customer was able to properly size only half their inventory of spares for reparable parts because nobody had been tracking when the other half was breaking down, meaning there was no information on mean time before failure (MTBF), meaning it was not possible to model the breakdown behavior of half the fleet of reparable spares.

Finally, the currency of data matters. As the speed of business increases and company planning cycles drop from a quarterly or monthly tempo to a weekly or daily tempo, it becomes desirable to exploit the agility provided by overnight uploads of daily transactional data into the cloud. This allows high-frequency adjustments of forecasts and/or inventory control parameters for items that experience high volatility and sudden shifts in demand. The fresher the data, the more trustworthy the analysis.

Trust in Demand Forecasting Software

Even with high-quality data, forecasters must still trust the analytical software that processes the data. This trust must extend to both the software itself and to the computational environment in which it functions.

If forecasters used on-premises software, they must rely on their own IT departments to safeguard the data and keep it available for use. If they wish instead to exploit the power of cloud-based analytics, customers must trust their confidential information to their software vendors. Professional-level software, such as ours, justifies customers’ trust through SOC 2 certification. SOC 2 certification was developed by the American Institute of CPAs and defines criteria for managing customer data based on five “trust service principles”—security, availability, processing integrity, confidentiality, and privacy.

What about the software itself? What is needed to make it trustworthy? The main criteria here are the correctness of algorithms and functional reliability. If the vendor has a professional program development process, there will be little chance that the software ends up computing the wrong numbers because of a programming error. And if the vendor has a rigorous quality assurance process, there will be little chance that the software will crash just when the forecaster is on deadline or must deal with a pop-up analysis for a special situation.

Summary

To be useful, forecasters and their forecasts must be trusted by decision-makers. That trust depends on characteristics of forecasters and their processes and communication. It also depends on the quality of the data and software used in creating the forecasts.

Read the 1st part of this Blog “Who do you Trust” here: https://smartcorp.com/forecasting/the-role-of-trust-in-the-demand-forecasting-process-part-1-who/

Service-Level-Driven Service Parts Planning for Microsoft Dynamics BC or F&SC is a four-step process that extends beyond simplified forecasting and rule-of-thumb safety stocks. It provides service parts planners with data-driven, risk-adjusted decision support.

The math to determine this level of planning simply does not exist in D365 functionality.  It requires math and AI that passes thousands of times through calculations for each part and part center (locations).  Math and AI like this are unique to Smart.  To understand more, please read on. 

Step 1. Ensure that all stakeholders agree on the metrics that matter. 

All participants in the service parts inventory planning process must agree on the definitions and what metrics matter most to the organization. Service Levels detail the percentage of time you can completely satisfy required usage without stocking out. Fill Rates detail the percentage of the requested usage that is immediately filled from stock. (To learn more about the differences between service levels and fill rate, watch this 4-minute lesson here.) Availability details the percentage of active spare parts with an on-hand inventory of at least one unit. Holding costs are the annualized costs of holding stock accounting for obsolescence, taxes, interest, warehousing, and other expenses. Shortage costs are the cost of running out of stock, including vehicle/equipment downtime, expedites, lost sales, and more. Ordering costs are the costs associated with placing and receiving replenishment orders.

Step 2. Benchmark historical and predicted current service level performance.

All participants in the service parts inventory planning process must hold a common understanding of predicted future service levels, fill rates, and costs and their implications for your service parts operations. It is critical to measure both historical Key Performance Indicators (KPIs) and their predictive equivalents, Key Performance Predictions (KPPs).  Leveraging modern software, you can benchmark past performance and leverage probabilistic forecasting methods to simulate future performance.  Virtually every Demand Planning solution stops here.  Smart goes further by stress-testing your current inventory stocking policies against all plausible future demand scenarios.  It is these thousands of calculations that build our KPPs.  The accuracy of this improves D365’s ability to balance the costs of holding too much with the costs of not having enough. You will know ahead of time how current and proposed stocking policies are likely to perform.

Step 3. Agree on targeted service levels for each spare part and take proactive corrective action when targets are predicted to miss. 

Parts planners, supply chain leadership, and the mechanical/maintenance teams should agree on the desired service level targets with a full understanding of the tradeoffs between stockout risk and inventory cost.  A call out here is that our D365 customers are almost always stunned by the stocking levels difference between 100% and 99.5% availability.   With the logic for nearly 10,000 scenarios that half a percent outage is almost never hit.   You achieve full stocking policy with much lower costs.   You find the parts that are understocked and correct those.  The balancing point is often a 7-12% reduction in inventory costs. 

This leveraging of what-if scenarios in our parts planning software gives management and buyers the ability to easily compare alternative stocking policies and identify those that best meet business objectives.  For some parts, a small stock out is okay.  For others, we need that 99.5% parts availability.  Once these limits are agreed upon, we use the Power of D365 to optimize inventory using D365 core ERP as it should be.   The planning is automatically uploaded to engage Dynamics with modified reorder points, safety stock levels, and/or Min/Max parameters.  This supports a single Enterprise center point, and people are not using multiple systems for their daily parts management and purchasing.

Step 4. Make it so and keep it so. 

Empower the planning team with the knowledge and tools it needs to ensure that you strike agreed-upon balance between service levels and costs.  This is critical and important.  Using Dynamics F&SC or BC to execute your ERP transactions is also important.  These two Dynamics ERPs have the highest level of new ERP growth on the planet.  Using them as they are intended to be used makes sense.   Filling the white space for the math and AI calculations for Maintenance and Parts management also makes sense.  This requires a more complex and targeted solution to help.  Smart Software Inventory Optimization for EAM and Dynamics ERPs holds the answer.    

Remember: Recalibration of your service parts inventory policy is preventive maintenance against both stockouts and excess stock.  It helps costs, frees capital for other uses, and supports best practices for your team. 

Extend Microsoft 365 F&SC and AX with Smart IP&O

To see a recording of the Microsoft Dynamics Communities Webinar showcasing Smart IP&O, register here:

https://smartcorp.com/inventory-planning-with-microsoft-365-fsc-and-ax/