This book is in Open Review. I want your feedback to make the book better for you and other readers. To add your annotation, select some text and then click the on the pop-up menu. To see the annotations of others, click the button in the upper right hand corner of the page

1.1 Forecasting, planning and analytics

While there are many definitions of what is forecast, I like the following one, proposed by Sergey Svetunkov (Svetunkov and Svetunkov, 2014): Forecast is a scientifically justified assertion about possible states of an object in future. This definition does not have the word “probability” in it, because in some cases forecasts do not rely on rigorous statistical methods and theory of probabilities. For example, Delphi method allows obtaining judgmental forecasts, typically focusing on what to expect, not on the probability side of things. An important word in the definition is “scientific.” If a prediction is done based on coffee grounds, then it is not a forecast. Judgmental predictions on the other hand can be considered as forecasts if a person has a reason behind them. If they do not, then they would be called “guesses,” not forecasts. Finally, the word “future” is important as it shows the focus of the discipline: without the future there is no forecasting, only overfitting. As for the definition of forecasting, it is a process of producing forecasts - as simple as that.

Forecasting is a very important activity, carried by many companies, some of which do that unconsciously or label it as “demand planning” or “predictive analytics.” There is a difference, however, between the terms “forecasting” and “planning.” The latter relies on the former and implies actions made by the company in order to adjust its decision. For example, if we forecast that the sales will go down, a company should make some marketing decisions in order to increase the demand on the product. The first part relates to forecasting, while the second one relates to planning. This also means that if a company does not like a forecast, it should change something in its activities, not in the forecast itself. It is important not to confuse these terms in practice, when important decisions are made.

Another important thing to keep in mind is that any forecasting activity should be done to inform decisions. Forecasting for the sake of forecasting is pointless. Yes, we can forecast the overall number of hospitalisations due to SARS-CoV-2 virus in the world for the next decade, but what decisions can be made based on that? If there are some decisions, then this exercise is useful. If not, then this is just a waste of time.

Example 1.1 Retailers typically need to order some amount of milk that they will sell over the next week. They do not know how much they will sell so they usually order, hoping to satisfy, let us say, 95% of demand. This situation tells us that the forecasts need to be made a week ahead, they should be cumulative (considering the overal demand during a week before the next order) and that they should focus on an upper bound of a 95% prediction interval. Producing only point forecasts would not be useful in this situation.

Related to this is the question of forecasts accuracy. In reality, the accurate forecasts do not always translate to good decisions. This is because there are many different aspects of reality that need to be taken into account, and forecasting focuses only on one of them. Capturing the variability of demand correctly is sometimes more useful than producing very accurate forecasts - this is because many decisions are based on distributions of values rather than on point forecasts. The classical example of this situation is the inventory management, where the ordering decisions are made based on quantiles of distribution to form safety stock. Furthermore, the orders are typically done in pallets, so it is not important, whether the expected demand is 99 or 95 units, if a pallet includes 100 units of a product. This means that whenever we produce forecasts, we need to keep in mind how they will be used and by whom.

In some cases, the very accurate forecasts might go to waste if people make decisions differently and / or do not trust to what they see. For example, a demand planner might decide that a straight line is not a good point forecast and would start changing the values, introducing noise. This might happen due to lack of experience, expertise or trust in models, and this means that it is important to understand who will use the forecasts and how.

Finally, in practice, not everything can be solved with forecasting. In some cases companies can make decisions based on other reasons. For example, promotional decisions can be dictated by the existing stock of the product that needs to be moved out. Another case, if the holding costs for a product are very low, then there is no need in spending time on forecasting the demand on it - a company can implement a simple replenishment policy, ordering, when stock reaches some threshold. And in times of crysis, some decisions are dictated by the financial situation of a company, not by forecasts: you do not need to predict demand on products that are sold out of prestige if they are not profitable and a company needs to cut the costs.

Summarising all above, before diving into forecasting, it makes sense to find out what decisions will be made based on it, by whom and how. There is no need to waste time and effort on improving the forecasting accuracy if the process in company is flawed and forecasts are then ignored, not needed or amended inadequately.

As for analytics, this is a relatively new term, which implies a set of activities based on analysis, forecasting and optimisation to support informed managerial decisions. The term is large and relies on many research areas, including forecasting, simulations, optimisation etc. In this textbook, we will focus on the forecasting side, occasionally discussing how to analyse the existing processes (thus touching the analytics part) and how various models could help in making adequate practical decisions.

References

• Svetunkov, I., Svetunkov, S., 2014. Forecasting methods. Textbook for universities. Urait, Moscow.