Warning Lights and Gauges

Posted on August 5, 2026 by Jeff Harrop

The signal is the truth. The noise is what distracts us from the truth. – Nate Silver

Do you know (in PSI or kPa) what a proper oil pressure reading is for your car? Or the correct voltage reading for your alternator? Or at what temperature your engine should be running?

I sure don’t and I’d wager that the vast majority of car owners don’t either. That’s why over time, measurement gauges on a car’s dashboard have been replaced (or augmented with) warning lights – something to let you know that there is a problem that requires your attention. (As an aside, my grandfather who was a mechanic for 50+ years used to refer to them as “idiot lights” – as if anyone who doesn’t readily know the answer to my questions above shouldn’t even be allowed to drive).

While it’s true that gauges provide more information (a range of possible values versus just a binary on/off signal), you really need to fully understand the capabilities and limits of the systems being measured to know what they’re actually telling you and – more importantly – if action is required based on the reading, which you would need to monitor constantly.

I have been in the supply chain planning game for over 30 years now and when I meet a new colleague for the first time, it’s not uncommon for him/her to lead with something like “Our forecast accuracy is 79.6%” (I suppose they must be looking for some sort of affirmation or praise).

What they end up getting is usually a confused look and about a thousand questions:

Are you measuring at item/location level then aggregating or aggregating then measuring?
What specific measurement are you using?
Over what time frame?
Are the errors biased in one direction or the other?
Etc., etc., etc.

However, the most important questions (which take some time to come to the surface) are:

How do you know if that’s good or bad?; and
What do you do with that information?

When you multiply the number of items through the number of locations for a retailer, there are a lot of forecasts being produced across fast sellers, slow sellers, seasonal items, highly promoted items, products at the beginning/end of their lifecycle, not to mention myriad combinations of all of those attributes.

There’s nothing mathematically invalid about aggregating numbers and dividing them by each other to come up with a percentage using the full data set, but there’s nothing intrinsically useful about it either. Unless – and this will sound a bit cynical – your goal is to produce a number that makes it appear as though the process is working beautifully, even though it may be completely skewed by very high volume and stable selling items that require no effort to forecast well.

Most importantly, it doesn’t give a true picture of the highly varied landscape that is retail forecasting and it’s not actionable.

The forecasts that matter are the ones that directly affect the customer experience – for each specific item at each specific location. I’ve discussed this before, but when you’re looking at the individual granular forecasts that actually run the supply chain, you need to be accurate, not precise (those are two different things). It means moving away from comparing a single forecast to a single actual and calculating percentages to determine distance from absolute perfection (a completely unreasonable yardstick to measure against).

It’s really about recognizing that for any given item at any given store at any given time, there is a range expected forecast values that can be considered high quality, depending on the nature of the product, the timing of the demand and the additional causals that might be in play at the time.

Think of it this way: If your forecast for an item at a store is 4 units for the week and you actually sold 2, your “accuracy” is 50%, which sounds bad. But is it really a bad forecast? Is there something you could have done in advance that would have led you to forecast a value closer to 4? Now that you know you missed by 2 units, what specific actions can you take to make sure the next forecast is closer? What you end up doing in this scenario is chasing noise – and in retail forecasting there is a lot of it.

However, at this level of volume, it’s probably quite common to miss by 3 units in either direction in any given week, just as a result of uncontrollable randomness. In other words, there is an expected and acceptable “distance from perfect” that applies to every forecast. To make your forecast measurement truly actionable and useful, you should be measuring actuals against this range to make this determination. So, in our example above, if the actual is 4 and the common range of error is +/- 3 units, then any forecast between 1 and 7 units would be considered accurate when compared against the actual.

If you use a probabilistic forecasting approach, these acceptable ranges can be calculated with the forecast itself. If not, there would need to be some upfront analysis to assign one to each forecast, but the end result is that you have a way to find the needles in the haystack: instead of knowing which forecasts have error (pretty much all of them), you instead know which forecasts have unexpectedly high error. That’s actionable information that can be chased down and investigated.

With each individual forecast classified in this way (essentially an accurate/inaccurate “warning light”), you can also present a more meaningful gauge on your high level dashboard. Instead of a number representing “distance from unattainable perfection in the aggregate”, you can instead report on percentage of forecasts out of error tolerance.

What’s the Impact of Your Promotions?

Posted on December 3, 2025 by Jeff Harrop

It’s the little details that are vital. Little things make big things happen. – John Wooden

As a retailer, how important are promotions to your business?

Whenever we engage with a new retail client, this is one of the first questions we ask. Promotions – particularly short term price promotions – can have a profound impact on the supply chain (think about trying to shove a basketball through a garden hose) and pretty much always requires some significant thought around processes to plan and execute them properly.

More often than not, we’ll get an answer along the lines of “We do 30% of our business on promotion.”

How do they come up with this number?

Virtually all modern point-of-sale systems will flag a sale as promotional when it is being transacted, which makes things pretty simple: Sum up all of your sales where a promotional code has been affixed by the POS system, divide it by your total sales for the same time period and voila – you get a percentage you can recite to anyone who asks.

But does that actually mean “you do 30% of your business on promotion” or does it just mean that 30% of the sales you transact have a promotion identifier applied by the POS system?

If the overall goal of promotions is to drive additional sales and traffic, you can’t really measure them against that goal unless you know (or can reasonably estimate) a number of things, beyond just the sales that were recorded:

How many customers were going to buy promotional items at full price that week anyhow?

How many customers were going to buy promotional items at full price in future weeks but purchased decided to purchase earlier and/or in larger quantities to take advantage of the promotional price?
How many customers were going to buy a different brand at full price, but switched to the brand that was on sale?
How many customers were going to pay full price for a different brand, but switched to a promotional item instead?
How many sales did you miss because a number of stores ran out of stock before the promotion ended?
Etc.

The specific impact of each of these consumer behaviours can vary item by item and store by store. Even worse, none of this information is stored in your POS system (or anywhere else), so if that’s all you have to work with, it’s really tough to understand the true impact of promotions on your business.

But what if you had a process and a system at item/store level that could:

Identify promotions and other events in your sales history; and
Estimate and isolate the incremental impact of those events for the purpose of developing a baseline forecast?

This would give you a view – for every item at every store – of what your sales would have been in each week that was impacted by a promotion:

A graph of a graph

AI-generated content may be incorrect.

The methods for calculating “sales that would have been” will differ, but this type of sales history cleansing/segmentation is standard functionality for virtually all forecasting systems. Putting aside the “how”, the “what” gives you what you need to better estimate promotional impact:

A graph with lines and text

AI-generated content may be incorrect.

So now in addition to knowing that you sold 31 units at the promotional price, you also know:

The actual uplift in sales during the promotion week was 22 units – in other words, had the promotion not happened, you would have still sold 9 units at regular price that week.
This store ran out of stock 5 days into the promotion. Had that not happened the actual sales could have been 40 units.
Because of customer hoarding behaviour (or perhaps the stockout mentioned above persisted into the next week or two), your regular price sales for the next few weeks after the promotion declined by 11 additional units.
When a competing item was on promotion a few weeks later, this item was cannibalized to the tune of about 15 units.

This is the story for one particular item at one particular store and in sales units only – and that’s the whole point. When you plan in this way at the most granular level, you can gain insights at every level above it that can help you with planning future promotions, by understanding:

What was our true incremental sales gain from promotions?
Was our incremental sales gain constrained due to out-of-stocks during promotional periods? How do we factor this into our forecasts and stocking plans for future promotions?
How much did we sacrifice in regular price sales and what was the true incremental profit gain from our promotional activity?
Does the incremental profit gain reasonably offset the additional costs of promoting items (advertising, signage, store labour, logistics costs, etc.)?

Knowing that promotions are key to your business is one thing. But knowing their true impacts and tradeoffs to sales and profitability can really help you make better decisions that will squeeze maximum value from your promotional activity.

Objections to Flowcasting

Posted on November 5, 2025 by Mike Doherty

I recently published an article about how Flowcasting was built on bedrock, rather than buzzwords. My argument is that the concept of Flowcasting is architected on a series of what I believe are timeless, fundamental supply chain planning principles. You know, like “never forecast what you can calculate”, and so on.

A reader sent me a note about the article, outlining two major objections to my thinking. Here’s what they said…

“Hello Mike, I have two major objections to this article:

First one is that “The entire retail supply chain (or any industrial supply chain) is driven only by a forecast of end consumption” is highly flawed. It does not consider lead time variability, and overall, any other kind of variability

Second one is the narrowed view of having one “valid future”. This assumes you are planning against a fixed demand scenario (most likely the average) while one cannot act as future demand is strictly known”

I was tempted to reply something like this… “Hello, thanks for the comments. Feel free to clear off with your negativity and lack of understanding.”

However, upon reflection, that seemed a tad harsh and didn’t address their queries. So, I decided a more proper response would be more appropriate.

Here it is, essentially…

“Hello. Objections are always welcomed, and thanks for your comments. What I was trying to do in the article was to outline the fundamental principles of Flowcasting and explain why I believe they have and will, endure.

In terms of your question regarding an industrial supply chain being driven by end consumption, I was referring to the disconnectedness in the retail supply chain. For example, it’s very common for a retailer to have one system/approach for stores, one for their DCs and no sharing of future projections to suppliers. Flowcasting connects it all in one integrated approach, using the principles of time-phased planning and Distribution Resource Planning (DRP) – the integrated supply chain is connected by dependent demand from consumption to supply. And, since the upstream nodes are dependent on their customer nodes, the entire supply chain can be connected by developing and maintaining an up to date forecast of end consumption. In retail, that’s a forecast of consumer demand, with all known demand influencers (e.g., promotions, etc.) factored into the forecast and the only forecast needed in the retail supply chain.

In response to your comments around variability, you are right – there is lots of variability in the retail supply chain, or any industrial supply chain. However, this is managed by supply chain constraints and stocking policies, which can be time-phased. Of course, forecasts will always be wrong and that’s one reason we plan using safety stock, or planograms at store level that aim to dampen the impacts of this variability, while keeping inventory available for consumers to purchase. For seasonal products, the variability in the weather (e.g., when will spring happen in the prairies in Canada) can be mitigated by planning inventory flows earlier than the season usually starts, just to ensure inventory is positioned for sale should the season break early.

In response to your question regarding lead time variability, a lot of it can be dramatically reduced by daily replanning and sharing those updated plans up and down the supply chain. From experience, if the retailer does a decent job of sharing stable supplier schedules (essentially projected purchases by product) with their merchandise suppliers, this helps suppliers deliver on time and to a consistent lead time. That’s also true for internal operations teams – since the Flowcasting projections are converted to their language of the business (e.g., cube, volume, capacity) then these teams can pick, pack and deliver to a consistent lead time. This is not theory; it’s happening today.

In terms of a valid view of the future, for operational purposes, Flowcasting uses a forecast of the “most likely” consumer demand. While probabilistic planning has many proponents (and I agree, I do see where it could be very helpful) at some stage, the supply chain is governed by actuals. For example, consumers don’t buy probabilities in stores – they buy products in specific quantities. Therefore, stock transfers/purchase orders flowing from the integrated Flowcasting plans have fixed quantities and the process calculates those quantities using the “most likely” estimate, built on top of policies that cover variability.

In summary, several retailers use what I would call the Flowcasting concept and have increased daily in-stock from the 92-94% range (the industry average) to 97-98% while also improving enterprise inventory performance and costs.”

So, to the respondent to my article, Thank You for the objections. They help me/us to better understand where people’s thinking is and give us the chance to respond – to hopefully either enlighten the reader or challenge us to improve the Flowcasting concept.

A win-win either way.

Four Hundred Forty-Nine

Posted on May 7, 2025 by Mike Doherty

“Failure is an option here. If you’re not comfortable with failure, you’re not comfortable with innovation.”
– Jeff Bezos

Unilever is a consumer-packaged goods giant. Several years ago, they had a serious production problem at one of their factories near Liverpool, in the north-west of England. They were making washing powder in the standard way – the way washing powder is still made today, where boiling chemicals are forced through a nozzle at very high speeds and as the pressure drops, they disperse into vapor and powder. Then, the vapor is siphoned off and the powder collected in a vat, where additional chemicals and ingredients are added and then sold as washing powders.

The problem Unilever had was that the nozzles didn’t work very well or smoothly – they kept clogging up. They were inefficient (causing numerous production delays), kept blocking and produced varying grains of powder, of different sizes. This was a major issue for Unilever, not just because of maintenance and lost time, but also in terms of the quality of the product which was rightly disappointing customers. They needed to develop a better nozzle. Much better.

So, they turned to an internal team of crackpot mathematicians. Unilever, like many large industrial giants, could afford the best and the brightest and had on staff a team of math folks who were experts in high-pressure systems and fluid dynamics. They were also experts in the physics of what is called “phase transition” – the process that governs the transformation of matter from one state to another (e.g., from liquid to gas).

The expert math team did what experts often do – they delved deep into the problem and developed sophisticated equations and solutions. After a long period of study and design, they came up with a new and what they believed was brilliant, design.

Problem was, it didn’t work. The powder granularity remained inconsistent, and the process was still inefficient.

In desperation, Unilever also turned to their team of biologists – a team with no knowledge of fluid dynamics and phase transitions. This team had something else that would prove crucial – a design approach that was rooted in experimentation. A test, fail and learn approach. One that seemed to understand that failure was part of learning, and often a necessity for innovation.

Instead of a brilliant design, they would make some minor tweaks, try it, see what worked and didn’t work, adjust and test again. Then, rinse and repeat, until they had a better nozzle that worked in practice, not just on paper.

They would take ten copies of the nozzle and apply a small change to each one, then test each one to see which ones failed, but importantly, which one performed the best. They would then take the “best” nozzle and do the same thing again: create ten slightly different copies and then repeat the process. Then repeat it again. And again. And again.

After 45 generations they had finally developed a nozzle that was excellent.

A world class nozzle had been built because of testing, discarding and improving upon four hundred forty-nine ‘failures’.

Progress/innovation had been achieved not by a grand, brilliant design, but instead by rapid interactions with the real world.

An approach, it turns out, that is fundamental to designing something better, even in supply chain management.

When it comes to inventory planning, people are embracing the concept of Flowcasting. That’s good. In my opinion, the breakthrough that’s made Flowcasting possible, is the capability to forecast, replenish and managing slow and super-slow selling items at store level.

The best solution to this chronic issue that had plagued planning system providers, was developed and architected by our long-time colleague, Darryl Landvater of the Oliver Wight Americas Team. And, largely by using the same approach as the biologists from Unilever – a test and learn approach, refining based on real-world learning’s, then doing it again and again until an elegant, intuitive solution was proven.

I won’t bore you with the details, but repeated tests and learning’s helped him understand and correctly conclude that managing slow sellers at the store level is simultaneously a forecasting and replenishment issue. His solution is the only approach that I know of that manages both the forecast and replenishment plan at store level in unison. It ensures a valid simulation of reality and, critically, that inventory can be maintained close to the store safety stock level for these types of items. That’s critical for a retailer, since most retailers have a significant percentage of slow sellers.

I’ve never asked Darryl how many ‘failures’ he endured on his journey to developing his slow seller solution, because it doesn’t really matter.

I’m just glad he did.

Forecasting Wordplay

Posted on April 3, 2024 by Jeff Harrop

If it is true that words have meanings, why don’t we throw away words and keep just the meanings? – Ludwig Wittgenstein via Anatol Holt

How do you describe your demand forecasts?

In retail, I’ve had numerous conversations that go something like this:

Me: “Do you really think you’re going to sell 10,000 units on that promotion? You’ve never sold higher than 8,000 at that price point.”

Retail Buyer/Demand Planner: “Yeah, it’s a bit optimistic.”

While less common, forecasts can also be made lower than one would expect (or “pessimistic”, if you will), particularly if an incentive structure exists where people are rewarded when actual sales blow the forecast out of the water.

While these “optimistic” or “pessimistic” numbers are entered into the forecasting system and potentially even drive the replenishment and supply planning functions, it would be a misnomer to call them forecasts.

Saying that a forecast is optimistic is an admission that you believe it’s biased to the high side for no good reason. You can call it a goal, a wish or a dream, but it is NOT a forecast.

In a similar way, a “pessimistic forecast” is a hedge, not a forecast.

Simply put, if you don’t truly believe the numbers you’re producing are a reflection of what’s actually going to happen, then you’re not forecasting. A true forecast is the prediction you’d make if you were obligated to bet $500 of your own money on the outcome.

That’s not to say that the most objective forecast produced by the most unbiased demand planner may not be way off. At its essence, demand planning applies assumptions in an attempt to predict human behaviour. That doesn’t always work out.

That’s also not to say that the words “optimistic” and “pessimistic” have no place in forecasting – so long as there are assumptions to back up the judgments.

For example, “I’m optimistic that we’ll beat last year’s sales, because we’ve sharpened our pricing and caused a key competitor to exit the market for this category.”

Or “I’m pessimistic about the sales outlook for our high price point luxury lines because the economy is in the tank and discretionary spending is going to be way down for the next 12 months.”

But what about the potential missed opportunities? What if we produce an unbiased, objective forecast and it ends up oversold to the point that we run out of stock and leave sales on the table?

Isn’t having a forecast that’s “a bit too high” much less risky in terms of being able to satisfy customer demand?

To be clear, a forecast is just one determinant of the level of stock needed to satisfy customer demand. The other is the uncertainty of the demand. If you apply the uncertainty to the supply side of the equation (i.e. safety stock), then that frees you up to forecast with objectivity.

Yes, the uncertainty needs to be quantified, but if you habitually describe your forecasts as being “optimistic” (which is a euphemism for “biased”), then you’re already doing that anyhow:

Optimistic Forecast = What we think customers might buy
Objective Forecast = What we think customers will buy
Safety Stock = Optimistic Forecast – Objective Forecast

A Forecast By Any Other Name

Posted on December 6, 2023 by Jeff Harrop

What’s in a name? That which we call a rose
By any other name would smell as sweet. – William Shakespeare (1564-1616), Romeo and Juliet, Act 2 Scene 2

Scenario 1: A store associate walks down the aisles. She sees 6 units of an item on the shelf and determines that more is needed on the next shipment, so she orders another case pack of 12 units.

Scenario 2: In the overnight batch run, a centralized store min/max system averages the last 6 weeks of sales for every item at every store. This average selling rate is used to set a replenishment policy – a replenishment request is triggered when the stock level reaches 2 weeks’ worth of on hand (based on the 6 week average) and the amount ordered is enough to get up to 4 weeks’ worth of on hand, rounded to the nearest pack size.

Scenario 3: In the overnight batch run, a centralized store reorder point system calculates a total sales forecast over the next 2 shipping cycles. It uses 2 years’ worth of sales history so that it can capture a trend and weekly selling pattern for each item/store being replenished and calculate a proper safety stock based on demand variability. On designated ordering days, the replenishment system evaluates the current stock position against the total of expected sales plus safety stock over the next two ordering cycles and triggers replenishment requests as necessary to ensure that safety stock will not be breached between successive replenishment days.

Scenario 4: In the overnight batch run, a centralized supply chain planning system calculates a sales forecast (with expected trend and weekly selling pattern) for the next 52 weeks. Using this forecast, merchandising minimums, store receiving calendars and the current stock position, it calculates when future arrivals of stock are needed at the store to ensure that the merchandising minimums won’t be breached over the next 52 weeks. Using the transit lead time, it determines when each of those planned arrivals will need to be shipped from the supplying distribution centre over the next 52 weeks. The rolled up store shipment projections become the outbound plans for each item/DC, which then performs the same logic to calculate when future inbound arrivals are needed and their corresponding ship dates. Finally the projected inbound shipments to the DC are communicated to suppliers so that they can properly plan their finished goods inventory, production and raw material procurement. For both stores and DCs, the plans are turned into firm replenishment requests at the ordering lead time.

With that out of the way, let’s do some audience participation. I have a question for you: Which of the above replenishment methods are forecast based? (You can pause here to scroll up to read each scenario again before deciding, or you can just look down to the very next line for the answer).

The answer is… they are ALL forecast based.

Don’t believe me?

In Scenario 1, how did the store associate know that a visual stock position of 6 units meant they were “getting low”? And why did she order a single case of 12 in response? Why didn’t she wait until there were 3 units? Or 1 unit? And why did she order 12? Why not 120?

For Scenario 2, you’re probably saying to yourself: “Averaging the past 6 weeks’ worth of sales is looking backward – that’s NOT forecasting!” Au contraire. By deciding to base your FUTURE replenishment on the basis of the last 6 weeks’ worth of sales, an assumption is being made that upcoming sales will be similar to past sales. That assumption IS the forecast. I’m not saying it’s a good assumption or that it will be a good forecast. I’m just saying that the method is forecast based.

Using the terms “trend” and “selling pattern” in Scenarios 3 and 4 probably spoiled the surprise for those ones.

So why did I go through such pains to make this point?

Quite simply, to counter the (foolish and naive) narrative that “forecasts are always wrong, so you shouldn’t bother forecasting at all”.

The simple fact is that unless you are in a position where you don’t need to replenish stock until AFTER your customer has already committed to buying it, any stock replenishment method you use must by definition be forecast based. I have yet to run across a retailer in the last 28+ years that has that luxury.

A forecast that happens in someone’s head, isn’t recorded anywhere and only manifests itself physically as a replenishment request is still a forecast.

An assumption that next week will be like the average of the last few weeks is still a forecast.

As the march continues and retailers gradually transition from Scenarios 1, 2 or 3 to Scenario 4, the forecasting process will become more formalized and measurable. And it can be a lot of work to maintain them (along with the replenishment plans that are driven by them).

But the overall effort pays off handsomely. Retailers in Scenarios 1, 2 and 3 have experienced in stock rates of 92-93% with wild swings in inventory levels and chronic stock imbalances. This has been documented time and again for 30 years.

Only by formalizing your forecasting your forecasting process, using those forecasts to drive long term plans and sharing those plans up and down the supply chain can you achieve 97-98% in stock while simultaneously reducing inventory investment, with reduced overall effort.

What Demand Planners Really Need

Posted on June 7, 2023 by Jeff Harrop

Necessity never made a good bargain. – Benjamin Franklin (1706-1790)

If you ask someone who thinks they know what a retail demand planner needs from a forecasting system, the response will likely be a list of features and gadgets that they believe will make forecasts “more accurate”. On the surface, this makes some sense – a more accurate forecast has greater planning value than a less accurate one.

Based on this perceived need, the hunt is on to buy a shiny new forecasting system for the demand planners to use. After some evaluations, the list is narrowed down to a couple of front runners. You send them your historical sales data and challenge them to a “bakeoff” – whoever produces the most “accurate” weekly forecast over a few cycles wins (or at least significantly improves their odds of winning).

And what do you learn from this process? You learn how good a bunch of nerds working for the pre-sales team are at fine tuning the inner workings of their system to produce the desired result they’re looking for – a new customer for their solution. How many person hours did they spend trying to win the sale? What exactly did they do to the models? Is any of what they did even remotely close to what a real demand planner can (and should) do on a daily basis to manage a large number of forecasts? You probably won’t learn any of this until the implementation team arrives after you sign on the dotted line.

What you will probably also learn is that each of the front runners produces a more accurate forecast for about 50% of the forecasts – likely with no clear reason as to why one did better than the other for a particular item in a particular location in a particular week. After rolling up all of the results, you find that one software provider’s accuracy is 0.89% higher overall than the other for the sample set used.

That’s when someone creates a fancy spreadsheet to “prove” that this extra 0.89% of “accuracy” actually equates to millions of dollars of additional benefits when you multiply it through all items at all locations and do a 10 year net present value on it. It’s all complete nonsense of course, but because it’s based on a tiny kernel of “truth” from the evaluation, it’s given outsized weight.

Fast forward to 3 years later. All of the real business challenges rear their ugly heads during the implementation and are solved with some compromises. Actual demand planners can’t seem to get the same “accuracy” results that were touted in the bakeoff. They don’t really understand all of the inner workings and don’t have the time that the pre-sales team had to fine tune everything in the same way. All of the press releases say that they now use Software X for demand planning, but in reality, most of the real work is being done in Excel spreadsheets, which the demand planners actually know how to use.

Now what if you asked demand planners directly what they actually need from a forecasting system? It’s really only 2 things: Comprehension and control.

Comprehension

When a demand planner is reviewing a system calculated forecast, they want to be able to say one thing: “Given the same inputs as the model, I would have come up with the same forecast on my own.”

That doesn’t mean that they agree with the forecast, it just means that they understand what the model was “thinking” to come up with the result. They don’t need code level understanding of the algorithms in order to do this, just knowledge of how the model interprets data and how it can be influenced.

Before they move a dial or switch to alter the model, they want to be able to reliably predict the outcome of their actions.

Control

So long as the behaviour of the model can be understood, a demand planner will want to work with it to get the output they want, rather than just give up and work against it with manual overrides they calculated in Excel.

Knowing what the model did and why it did it is important, but demand planners also need to know how to affect changes in the model to make it behave differently, but also predictably so that the system will produce forecasts that they agree with and for which they are willing to be held accountable.

Accuracy is a rearview mirror measure. Demand planners need to be able to live in the future, not the past. In order to support them, a forecasting system needs to be both understandable and directly controllable so that they can fully accept accountability for the outcome.

Probabilistic Forecasting – One Man’s (Somewhat Informed) Opinion

Posted on April 5, 2023 by Jeff Harrop

A reasonable probability is the only certainty. – E. W. Howe

My, how forecasting methods for supply chain planning have evolved over time:

Naive, flat line forecasts (e.g. moving averages) were once used to estimate demand for triggering orders.
Time series decomposition type mathematical models added more intelligence around detecting trends and seasonality to enable better long term forecasting.
Causal forecasting models allowed different time series to influence each other (e.g. the effect of future planned price changes on forecasted volumes)

All of these methods are deterministic, meaning that their output is a single value representing the “most likely outcome” for each future time period. Ironically, the “most likely outcome” almost never actually materializes.

This brings us to probabilistic forecasting. In addition to calculating a mean (or median) value for each future time period (can be interpreted as the most likely outcome), probabilistic methods also calculate a distinct confidence interval for each individual future forecast period. In essence, instead of having an individual point for each time period into the future, you instead have a cloud of “good forecasts” for various types of scenario modeling and decision making.

But how do you apply this in supply chain management where all of the physical activities driven by the forecast are discrete and deterministic? You can’t submit a purchase order line to a supplier that reads “there’s a 95% chance we’ll need 1 case, a 66% chance we’ll need 2 cases and a 33% chance we’ll need 3 cases”. They need to know exactly how many cases they need to pick, full stop.

The probabilistic forecasting approach can address many “self evident truths” about forecasting that have plagued supply chain planners for decades by better informing the discrete decisions in the supply chain:

That not only is demand variable, but variability in demand is also variable over time. Think about a product that is seasonal or highly promotional in nature. The amount of safety stock you need to cover demand variability for a garden hose is far greater in the summer than it is in the winter. By knowing how not just demand but demand variability changes over time, you can properly set discrete safety stock levels at different times of the season.
That uncertainty is inherent in every prediction. Measuring forecasts using the standard “every forecast is wrong, but by how much” method provides little useful information and causes us to chase ghosts. By incorporating a calculated expectation of uncertainty into forecast measurements, we can instead make meaningful determinations about whether or not a “miss” calculated by traditional means was within an expected range and not really a miss at all. The definition of accuracy changes from an arbitrary percentage to a clear judgment call, forecast by forecast, because the inherent and unavoidable uncertainty is treated as part of the signal (which it actually is), allowing us to focus on the true noise.
That rollups of granular unit forecasts by item/location to higher levels for capacity and financial planning can be misleading and costly. The ability to also roll up the specific uncertainty by item/location/day allows management to make much more informed decisions about risk before committing resources and capital.

Now here’s the “somewhat informed” part. In order to gain widespread adoption, proponents of probabilistic methods really do need to help us old dogs learn their new tricks. It’s my experience that demand planners can be highly effective without knowing every single rule and formula driving their forecast outputs. If they use off the shelf software packages, the algorithms are proprietary and they aren’t able to get that far down into the details anyhow.

What’s important is that – when looking at all of the information available to the model – a demand planner can look at the output and understand what it was “thinking”, even if they may disagree with it. All models make the general assumption that patterns of the past will continue into the future. Knowing that, a demand planner can quickly address cases where that assumption won’t hold true (i.e. they know something about why the future will be different from the past that the model does not) and take action.

As the pool of early adopters of probabilistic methods grows, I’m looking forward to seeing heaps of case studies and real world examples covering a wide range of business scenarios from the perspective of a retail demand planner – without having to go back to school for 6 more years to earn a PhD in statistics. Some of us are just too old for that shit.

I see great promise, but for the time being, I remain only somewhat informed.

Your Sales Plan is NOT a Forecast!

Posted on August 4, 2021 by Jeff Harrop

Man is the only animal that laughs and weeps, for he is the only animal that is struck with the difference between what things are and what they ought to be. – William Hazlitt (1778-1830)

A Ferrari has a steering wheel. A fire truck also has a steering wheel.

A Ferrari has a clutch, brake and accelerator. A fire truck also has a clutch, brake and accelerator.

Most Ferraris are red. Most fire trucks are also red.

A new Ferrari costs several hundred thousand dollars. A new fire truck also costs several hundred thousand dollars.

Ergo, Ferrari = Fire Truck.

That was an absurd leap to make, I know, but no more absurd than using the terms “sales plan” and “sales forecast” interchangeably in a retail setting. Yes, they are each intended to represent a consensus view of future sales, but that’s pretty much where the similarity ends. They differ significantly with regard to purpose, level of detail and frequency of update.

Purpose

The purpose of the sales plan is to set future goals for the business that are grounded in strategy and (hopefully) realism. Its job is to quantify and articulate the “Why” and with a bit of a light touch on the “What” and the “How”. It’s about predicting what we’re trying to make happen.

The purpose of the operational sales forecast is to subjectively predict future customer behaviour based on observed customer demand to date, augmented with information about known upcoming occurrences – such as near term weather events, planned promotions and assortment changes – that may make customers behave differently. It’s all about the “What” and the “How” and its purpose is to foresee what we think is going to happen based on all available information at any one time.

Level of Detail

The sales plan is an aggregate weekly or monthly view of expected sales for a category of goods in dollars. Factored into the plan are category strategies and assumptions (“we’ll promote this category very heavily in the back half” or “we will expand the assortment by 20% to become more dominant”), but usually lacking in the specific details which will be worked out as the year unfolds.

The operational sales forecast is a detailed projection by item/location/week in units, which is how customers actually demand product. It incorporates all of the specific details that flow out of the sales plan whenever they become available.

Frequency of Update

The sales plan is generally drafted once toward the end of a fiscal year so as to get approval for the strategies that will be employed to drive toward the plan for the upcoming year.

The operational sales forecast is updated and rolled forward at least weekly so as to drive the supply chain to respond to what’s expected to happen based on everything that has happened to date up to and including yesterday.

“Reconciling” the Plan and the Forecast

Being more elemental, the operational forecast can be easily converted to dollars and rolled up to the same level at which the sales plan was drafted for easy comparison.

Whenever this is done, it’s not uncommon to see that the rolled up operational forecast does not match the sales plan for any future time period. Nor should it. And based on the differences between them discussed above, how could it?

This should not be panic inducing, rather a call to action:

“According to the sales plan that was drafted months ago, Category X should be booking $10 million in sales over the next 13 weeks.”

“According to the sales forecast that was most recently updated yesterday to include all of the details that are driving customer behaviour for the items in Category X, that ain’t gonna happen.”

Valuable information to have, is it not? Especially since the next 13 weeks are still out there in a future that has yet to transpire.

Clearly assumptions were made when the sales plan was drafted that are not coming to pass. Which assumptions were they and what can we do about them?

While a retailer can’t directly control customer behaviour (wouldn’t that be grand?), they have many weapons in their arsenal to influence it significantly: advertising, pricing, promotions, assortment, cross-selling – the list goes on.

The predicted gap between the plan and the forecast drives tactical action to close the gap:

Maybe it turns out that the tactics you employ will not close the gap completely. Maybe you’re okay with it because the category is expected to track ahead later in the year. Maybe another category will pick up the slack, making the overall plan whole. Or maybe you still don’t like what you’re seeing and need to sharpen your pencil again on your assumptions and tactics.

Good thing your sales plan is separate and distinct from your sales forecast so that you can know about those gaps in advance and actually do something about them.

Your Forecast is Wrong (and That’s Okay)

Posted on June 2, 2021 by Jeff Harrop

Just because you made a good plan, doesn’t mean that’s what’s gonna happen. – Taylor Swift

I was 25 years old the first time I met with a financial advisor. I was unmarried, living in a small midtown Toronto apartment and working in my first full time job out of university.

I can’t say I remember all of the details, but we did go through all of the standard questions:

Will I be getting married? Having kids? How many kids?
How do I see my career progressing?
When might I want to retire?
What kind of a lifestyle do I want to have in retirement?

On the basis of that interview, we developed a savings plan and I started executing on it.

The following is an abridged list of events that have happened since that initial plan was created a quarter century ago, only a couple of which were accounted for (vaguely) in my original plan:

I left my stable job to pursue a not-so-stable career in consulting
I moved from my first apartment to a slightly larger apartment
I got married
We moved into an even bigger apartment
We had a kid
We moved into a house
We had two more kids
I co-authored a book
My wife went back to school for her Masters
The 2008 financial crisis happened
The Canadian government made numerous substantial changes to personal and corporate tax rules and registered savings programs
We sold our house and built a new house
Numerous cars were bought, many of which died unexpectedly
COVID-19 happened

You get the idea. Many of these events (and numerous others not listed) required a re-evaluation of our goals, a change in the plan to achieve those goals or both.

The key takeaway from all of this is obvious: That because the original plan bears no resemblance to what it is today, planning for an unknown and unknowable future is a complete waste of time.

At this point, you may be feeling a bit bewildered and thinking that this conclusion is – to put it kindly – somewhat misinformed.

I want you to recall that feeling of bewilderment whenever you hear or read people saying things (in a supply chain context) like “You shouldn’t be forecasting because forecasts are always wrong” or “Forecasting is a waste of time because you can’t predict the future anyhow”.

This viewpoint seems to hinge on the notion that a forecast is not needed if your minimum stock levels are properly calculated. To replenish a location, you just need to wait until the actual stock level is about to breach the minimum stock level and automatically trigger an order. No forecasting required!

Putting aside the fact that properly constructed and maintained forecasts drive far more than just stock replenishment to a location, a bit of trickery was employed to make the argument.

Did you catch it?

It’s the “minimum stock levels are properly calculated” part.

In order for the minimum stock level for an item at a location at any point in time to be “properly calculated”, it would by necessity need to account for (at a minimum):

The expected selling rate
Expected trends
Selling pattern (upcoming peaks and troughs)
Planned promotional and event impacts
Planned price changes
Etc.

Do those elements look at all familiar to you? A forecast by any other name is still a forecast.

The simple fact is that customers don’t like to wait. They’re expecting product to be available to purchase at the moment they make the purchase decision. Unless someone has figured out how to circumvent the laws of time and space, the only way to achieve that is to anticipate customer demand before it happens.

It’s true that any given prediction will be “wrong” to one degree or another as the passage of time unfolds and the correctness of your assumptions about the future are revealed. That’s not just a characteristic of a business forecasting process – it’s a characteristic of life in general. Casting aspersions on forecasting because of that fact is tantamount to casting aspersions upon God Himself.

It’s one thing to recognize that forecasts have error, it’s quite another to argue that because forecasts have error, the forecasting process itself has no value.

Forecasting is not about trying to make every forecast exactly match every actual. Rather it’s a voyage of discovery about your assumptions and continuously changing course as you learn.