AI to improve demand forecasting?

"Do you want to improve your demand forecasting capabilities?

I have developed a new way to use machine learning to support supply chains. Here's how it works:

I have developed a metamodel capable of dealing with virtually any supply chain demand data set. The metamodel will work with your data to create the best possible ML model."

This is the beginning of a post on Linkedin published on October 12, 2021. The promise is basically "I will improve your forecast with artificial intelligence (AI)".

And I ask, what do we really gain if this were possible? I'm not even questioning whether an "automated learning" algorithm is capable of improving forecast accuracy. My question is even more fundamental. Suppose if it does improve the forecast, what have we gained?

Determinants of inventory size

Inventory is necessary only if customers do not have the patience to wait for the product from the moment they express their need, so the objective of having inventory is to satisfy immediate sales. And we also know that the demand for a particular product at a point of sale has a high variability.

If the objective is to satisfy sales and demand has wide fluctuations, then the inventory we require must be sufficient to satisfy the maximum demand before the next replenishment, which means that most of the time we must hold inventories in excess of the actual demand at the time.

The next replenishment will depend on the time we decide to allow between replenishments, and also on how long it takes for the product to arrive after we order it. Both times together make up the replenishment time.

The longer the replenishment time, the bigger the inventory needed.

Consequences of a large inventory

The larger the inventory, the more space is required to store it, and the more tied-up capital we have. Since space and capital are both limited resources, the larger the inventory, the less variety we can offer customers, which reduces sales.

In addition, if the replenishment time is long, then we will also have higher risks associated with the inventory: risk of scrap and risk of obsolescence. In addition, a lower overall ROI of the operation.

Impact of the forecast on the consequences of the inventory

If our forecast is way off, we will have lost sales due to stock out, and we will have excess inventory accumulation.

If we improve the forecast, we will reduce the stock out, and also the accumulation of excess. However, the main factor that determines the size of the inventory is the replenishment time, and a lower forecast error does not reduce this factor at all, so the required inventory remains high.

I stop here for a minute, because I can already hear the counter argument "if the forecast is accurate, I need what is fair and necessary". I agree. But remember that demand is highly variable: some SKUs will have high sales in the period and others less so, and they alternate. For a particular period, the inventory required is the combination of high and low demand multiplied by a long time.

Why did I deduce that the time is long? Very easy, how many selling days does one need to forecast and how often does one forecast a product line? Once a week, once a month, every other month? It's not every day for all SKUs, that I think is pretty safe to assume.

Therefore, if I am using forecasts, it is very certain that the replenishment time is long. And even worse, if in addition to forecasts, I use MIN/MAX, the time to replenishment is also variable, so you should also forecast how long it will be until the next replenishment. And I am still accepting that we can improve the forecast.

From this reasoning, I deduce that a more accurate forecast, without changing anything else, has not reduced much space or capital tied up. Suppose that the improved forecast eliminates the stock out, and sales increase. The capital tied up will not be reduced very significantly. Remember that before there were stock outs, which means less inventory. Now there is more inventory of those products and less of the others, but the total effect is that inventory is still proportional to replenishment time, so it cannot be reduced very much.

What determines the profitability of a company?

Maybe I should have started here. A company is a system and its profitability depends on how much margin we can generate with its scarcest resources. Another way to look at it is how much money can be generated for every penny spent on trading.

In TOC - Theory of Constraints, Dr. Goldratt defined only three ways to measure money in a company: throughput, inventory, operating expense.

Throughput is the speed of generating money through sales. Inventory is the amount of money trapped in the system and can be converted into throughput. Operating expense is the money spent to convert inventory into throughput

I know that inventory defined in this way can be confusing. Let's use investment instead, and leave the term inventory for the units of products stored.

In mathematical optimization (linear and nonlinear programming), an objective function of the system is defined. In the case of a company, it is the profit. And that function would give infinity if it were not for the fact that the company's resources are limited, so we say that the optimum is determined by the active constraints.

In systems we already know that most of the resources must have slack (see refutation to line balancing) so there are only a few active constraints.

Thus, a company's profitability is determined by what its active constraints are and how they are used.

Space and capital are two constraints that are used more or less depending on the size of the required inventory. If the inventory needed is larger, these two constraints are being used more, even to the point of exhaustion. In that case we are forced to accept a level of stock out because we cannot increase inventory.

Relationship of forecast and profitability

As we have already seen, using forecasts is associated with a long replenishment time, so the aforementioned constraints, space and capital, will be used almost to the maximum. Now it is time to answer, how does better forecasting improve profitability?

A better forecast will make us use those space and capital constraints better, but it will not make us use them less. That is, if they are active constraints, we will be able to "move the needle a little" with more sales by reducing stock outs, but not much more, because the replenishment time has not changed and we will continue to use a lot of those constraints.

What if we reduce the replenishment time?

By reducing replenishment time we immediately alleviate the need for inventory to meet maximum demand. In other words, we can have fewer units of inventory and at the same time that inventory is proportionally larger than the previous one. This reduces stock out and reduces the use of space and capital constraints simultaneously.

By reducing the use of constraints, we can now exploit those constraints in a better way by expanding variety, for example, achieving much higher sales.

In a typical retail environment, outlets can restock every day from their distribution center. And I don't think I'm wrong when I say that outlets receive merchandise every day. What happens is that the fundamental change is that we replenish all SKUs every day.

How does a better forecast make a difference now if we are no longer coping with space or capital constraints? I don't think it makes any difference. And for such a short time, the best forecast is to repeat the immediate past: replenish today what was consumed yesterday.

But there may be changes in demand for each SKU, and inventory levels may not be adequate over time. For that we need to detect in which direction the demand is moving, but we do not require an exact number of units to be replenished. At TOC we have a simple mechanism we call Dynamic Buffer Management, which can be automated and adjusts the investment according to the actual demand. This is the origin of what has been called "Demand Driven".

One feature of this system is that it requires effort only to collect the daily data, which is already collected anyway. And no time is spent processing it, because it is done by a computer (although it is good that there is always human supervision).

When is it appropriate to forecast demand?

The capacity decision is a strategic decision. Normally capacity cannot easily be varied by significant amounts. Doubling or halving are moves that cannot be made frequently and require requirements planning. It is for this type of decision that S&OP (Sales and Operations Planning) is required.

At the capacity level there is a lot of statistical aggregation. It's easy to deduce that. If a company makes 3000 different SKUs, it will hardly have hundreds of production lines. A very large factory has less than ten lines, so the demand for each line has a lot of statistical aggregation. That also makes it possible to deduce that the aggregate demand forecast for each line has a much smaller error than the sales forecast for each SKU.

In such circumstances it is advisable to make demand forecasts to plan capacity expansions. The difficulty in this topic is how people do not understand the exponential function, but that is a topic for another article.

On the other hand, the complexity of today's supply chains also lends itself to AI applications to study capacity utilization at different nodes, such as factories, means of transport, ports, containers, etc. In that field, it is very impressive what Throughput Inc. has achieved with its ELI application (I think in honor of Eli Goldratt).

Conclusion

If I am offered a system to improve demand forecasting for replenishment at the points of sale, I already know that it is a system that operates with long replenishment times for each SKU, so I cannot expect a great improvement in profitability. Yes, there will be an improvement, but not a big one.

On the other hand, without any demand forecasting system, but with a dynamic buffer adjustment system, with short replenishment times, the improvement in profitability will be the same or better than that of the other system, but with less effort and less capital, and in addition to the release of constraints to generate even more margin.

What do managers believe in?

"A fill rate higher than 94%? Impossible! It is not possible to sustain it with an acceptable cost".

It is not the first time and I believe it will not be the last time I hear this type of statement when I talk to general managers. The fact is that they are intelligent and experienced people, which has led them to have certain convictions that allow them to make decisions quickly, without spending their scarce time on fantasies.

But what is it that happened in the past that led him to be convinced that it is not possible to have a fill rate close to 100% and at the same time be profitable?

What is fill rate?

This is a term commonly used in logistics to measure the degree of order fulfillment. In its simplest and most acidic expression, it is the percentage of order lines that have been completely fulfilled.

Of course, if the order has only two items of, say 900 units of the first and 100 units of the second, and we deliver 800 units and 100 respectively, with this definition we could have a fill rate of 50%. Then we can refine our definition by considering the quantities as well. One way is to calculate the fill rate as the units delivered divided by the total. In this case we would have 90%.

But if the 900 units represent 50% in money, we could now make another calculation that gives us 94.4%.

You see, fill rate is a KPI that can mean different things, but even so, that manager considered it impossible to sustain it above 94%.

How are decisions shaped?

The case I am relating is that of a consumer goods manufacturer that sells its production to a supply chain, where there are wholesalers, distributors and retailers.

In that company, as in many others, the managers are highly educated and have certainly learned the most well-known cost optimization techniques for the management of consumer goods companies. Among others, balancing production lines, using MIN/MAX and EOQ, and unit costing with the latest ABC (activity-based costing) techniques.

When one uses these techniques, the inevitable result is that capacity is barely sufficient to meet demand and a lot of inventory is accumulated. The inventory backlog uses two fundamental resources: warehouse space and working capital. When there is too much inventory, both resources are at their limit, so suggesting to increase inventory immediately increases the cost of the operation.

What does that have to do with the fill rate?, you ask.

Let's see, if there is a lot of inventory accumulated, that necessarily means more days of sales. In other words, the production schedule must consider a sales horizon farther into the future, so it is increasingly dependent on the accuracy of the forecast. The only thing we know for sure about the forecast is that it is wrong, so those production plans will end up with some items out of stock, resulting in a lower fill rate. Translated with www.DeepL.com/Translator (free version)

But it is even worse: every time an order is missing an item, there are production reschedules, which wastes capacity and now we have to pay a higher cost to achieve the entire production plan.

And don't managers realize this vicious circle?

It's easier to ask than to answer. How can they know that this is a vicious cycle? Or better, how could they know that they are not optimizing the operation? After all, they are following "best practices" and applying basic principles that are taught to this day in very prestigious universities.

And they are concepts practiced by many others in the industry.

After several years of optimization, this company has achieved 94% as a realistic and sustainable maximum. Every time they tried to improve it, maintaining the productive optimizations, inventories rose so much and so many shrinkages appeared, that the logical conclusion is that trying to improve the fill rate is not profitable, and it is not realistic to suggest it after so much experience that proves the opposite.

Is there a way out?

This is a question asked by a non-conformist. Someone who does not accept the trade off between fill rate and cost. Dr. Goldratt taught me not to accept contradictions; that a scientist must think until he eliminates them. Genrich Altshuller also thought this way, putting as the basis of TRIZ the conviction that an invention arises from eliminating a technical contradiction.

I refer to two previous articles to see how they invalidate some of the basic concepts that managers continue to use. See Refutation of line balancing and MIN/MAX and EOQ fallacy to know why these concepts are wrong.

In general, the major problem in business management today is a lack of awareness of the systemic nature of organizations. These examples presented here are just a sample.

The way out of the suboptimal fill rate problem is to question the concepts that give rise to day-to-day factory and supply chain decisions. By abandoning these "beliefs", another set of policies must be adopted. Fortunately, we have already been down that road, and we know what the new concepts and new policies are. And we have seen hundreds of companies (perhaps thousands) that in the last 30 years have achieved a fill rate close to 100% while reducing costs and inventories. Translated with www.DeepL.com/Translator (free version)

Why is the adoption of systems thinking slow?

Russell Ackoff answered this question several years ago in a short article. And he gave two reasons, one general and one specific.

The general reason has to do with the prevailing education, where mistakes are punished, from school, through college, and into the workplace. And the safest way to minimize the number of mistakes is to minimize the number of opportunities to make them. At least that's one of the strategies. Therefore, the survival instinct and the little urgency to do something new leads most people to avoid profound changes. And adopting systems thinking, also in the words of Dr. Ackoff, is a change of era: the paradigms to be changed are so profound and numerous that it is equivalent to changing the set of shared beliefs of a large group of people; it is a change in their worldview.

Why "take a chance" on something that contradicts the mainstream? To some extent this position is defensible.

The specific reason is related to systems thinking itself, where experts gather at conferences to present their research and cases in a jargon that is almost hermetic to the rest.

I agree more with the former than the latter, although it is true that sometimes the technical jargon is scary, but it cannot be the main reason.

Blocking fears

Before his departure, Dr. Goldratt wrote a preface to the book he was unable to write on the science of management. In that preface he talks about three fears that provoke behaviors in many managers. It is up to the manager to what degree each one affects him or her.

The first is the fear of complexity. The consequence is that the manager divides the system into parts thinking that it is simpler to manage each one separately.

The second is the fear of uncertainty, so the manager seeks to have control at a higher level of detail, thinking that he can better deal with variability.

The third is the fear of conflict, where the manager seeks an amicable solution to the numerous conflicts that arise in the company, which in practice translates into compromise.

Conclusion

With a very complex work experience, where he has never experienced what it means to eliminate conflicts and manage a complex system in a simple way, where uncertainty only grows and increases the complexity of the system, the manager clings to the few certainties he has, those he acquired in his studies, as if they were dogmas.

I invite all readers to review their own beliefs, at least in business management, and trust more in their reasoning ability. You will be pleasantly surprised.

en_US