Realistic Business Forecasting

By Adam Simmons

Paperback ISBN 9781912777396

'Realistic Business Forecasting' bridges the gap between the academic methodology of forecasting and the practical application of these techniq

• Language: English
• Publisher: U P Publications
• Release date: Aug 12, 2020
• ISBN: 9781912777402

Adam Simmons

ADAM SIMMONS MBA MSc BSc has combined a global career in the transportation sector, for public and private sector clients (working on the financial and economic aspects of projects worldwide), with almost 30 years in academia. He has taught on a range of quantitative and qualitative subjects, at post-graduate level.

Book preview

1. INTRODUCTION

Why this book?

I have been involved in forecasting for over 35 years and have seen what I can only describe as crimes against statistics over the course of my professional career. To give the reader an understanding of what I mean, consider the example in Figure 1-1. The figure is a reasonably accurate facsimile of a rail freight demand forecast I came across thirty years ago.

Figure 1-1: Rail Demand in an African Country

The report was written in 1990 and railway traffic had been in steady decline. However, demand was forecast to change direction in a way which I could only consider to be miraculous! There is a long list of factors which will have influenced the decline in demand:

Deteriorating economy

Government trade policy (most of the traffic was international or transit rather than domestic)

Weak management

Competition from substitutes (road in this case)

Quality of the infrastructure

Price and

Quality of service

Were the authors of the report really suggesting that many or most of these factors could turn positive in the space of a year or two and so reverse the declining trend?

The answer is almost certainly no. The list above contains factors which are beyond the control of the forecasters, but what about the forecasters themselves?

A common error in forecasting is to introduce optimism bias, a tendency to generate forecasts which over-emphasise the positive aspects of the entity. Forecasts undertaken by the UK’s Office for Budget Responsibility (OBR) neatly illustrates this point in Figure 1-2.

Figure 1-2: Optimism Bias in Productivity Forecasts

Source: https://obr.uk/learning-forecast-lessons/ Contains public sector information licensed under the Open Government Licence v3.0.

The figure shows that every forecast undertaken by OBR has been too optimistic with regards to the future trajectory of productivity in the UK. Such optimism bias is a widespread phenomenon and is practised by governments and businesses alike.

Why Bother with Forecasting?

Short-Term

As we have just seen, forecasting is an exercise prone to error, so why go to all the trouble? Indeed, one of my abiding memories, from university, is one of the lecturers saying that you can’t be right, but you can be wrong. The example in Figure 1-1 is a great example of being wrong!

First, many people assume that the core purpose of forecasting is to provide information which is as accurate as possible about future events.

This is certainly true of some forecasts; if we see that tomorrow’s weather forecast shows a significant increase in temperature and brighter, sunnier weather than today, then the way we dress will be different from a forecast which predicts cold and rainy weather.

In a business environment, short-term forecasting is necessary to schedule staff or stock to meet expected customer demand.

Weather forecasts are critical in certain sectors, such as transport, just-in-time inventory management and assessing demand for weather-sensitive products and services. As a rule, it is a reasonable expectation that short-term forecasting should be accurate. If patterns of trend and seasonality in the data have been established, then developing accurate forecasts ought to be straightforward.

However, as Chapter Shocks Explained will demonstrate, forecasts are subject to what can be termed shocks and, for any forecast, there is always going to be an element of randomness.

Indeed, the philosophy behind forecasting techniques is to develop models which explain historical data as much as possible and hence minimise the proportion of variation which is attributable to the random behaviour of sales, traffic density, temperature, etc.

Long-term Forecasting

Long-term forecasting, by contrast, is important when undertaking investment. If a retail company is considering opening a new outlet, for example, it will want to ensure that the asset is profitable over its life. It will need to forecast demand, utility and HR costs over several years. Of course, all these figures may turn out to be inaccurate – demand, in particular, is a very challenging element to forecast - but, nevertheless, it is the basis on which investment is appraised.

Forecasting for infrastructure is particularly challenging.

The life of an airport, sewage system or power station is measured in decades rather than years and the further into the future forecasts are, the less accurate they will be. Similar considerations apply to the development of a new product or service. A new prescription drug has research costs in excess of $2 billion and the Airbus-A350 series has reportedly booked some $15 billion to development costs.

Of course, not all new products cost this sort of money and both pharmaceutical and aircraft manufacturers are very large companies. Equally, a smaller company wishing to risk $1 million on a new product can face similar risks of financial failure, as they have much less access to capital than larger firms.

Long-term forecasting is also required when there is a response lag; in other words, when an external factor can take time to makes its impact felt on a business. For example, a change in interest rates can affect the economy over a period of up to three years as the consequences of the change work their way through business decisions. Such decisions include businesses considering whether to change a company’s level of borrowing or mortgage holders seeking a better deal by switching providers.

Focus on Food

This book includes an extended example of a company based on a fictitious supermarket chain. The reason for selecting this business sector is that it is one which most of us will find familiar and with which we have regular contact and easy access to real data.

Don’t think this book is now inappropriate because of this focus on a specific sector, consider the following exchange. Many years ago (1995, since you ask!) I was in conversation with two shipping sector experts who told me that shipping is special. My response, now, would be the same that I gave them, then, which was "every industry has as much the ‘same’ as it has ‘different’.

Allow me to explain what I meant. Disparate industries will follow various business cycles; degrees of competition will differ, as will volumes traded internationally; extent of government intervention; speed of innovation, and so on. But it is precisely these factors which make all industries similar, at a high level at least: all businesses within a particular industry need to be aware of the environment in which they operate and the extent to which individual firms can influence or at least react to these macro-environmental factors (i.e. those beyond the control of the firm).

Thus, although one industry has been highlighted in this book, the guidance provided can be applied to any firm or industry.

The ‘Missing Link’

Readers familiar with the subject of business strategy will notice how many topics in this book come from that discipline. Having combined consultancy with academia for more than 25 years, I am particularly keen on the way that academic frameworks can be applied in the commercial world. Even when quantitative methods, statistics or econometrics are taught within a business school alongside non-quantitative subjects, the two subject areas are often not particularly well linked.

To provide an example, I selected at random a plastic waste recycling company one of whose strengths was that "the company has excellent relationships with firms that collect and distribute PET bottles".

Assuming that these relationships are superior to those of competitors, how does this strength translate into a forecast? Will these superior relationships affect costs, revenues or both?

These are anything but easy questions to address but it would be unwise to ignore how softer issues affect future demand and profitability. After all, a company does not undertakes a SWOT¹ analysis as an academic exercise but as a means to build on its strengths relative to competitors, to eliminate (or at least mitigate) relative weaknesses and to assess factors in the macro-environment which the firm can use to its advantage or against which it can build defences.

The ‘missing link’ mentioned in the title of this section is how all these factors are related to forecasting.

The book covers both long and short-term forecasting.

Although the two timeframes have various quantitative techniques in common, the objectives of long-term forecasting are very different from short-term variants. This book is an attempt to bridge these divides.

The Modelling Process

Objectives of a Model

A model should ideally be simple yet comprehensive, capturing as many aspects of the real world which the model is intended to mimic. A model should also be accurate; clearly, accuracy cannot be promised for the future, but a model which is able to simulate the present and past, as closely as possible, will give confidence that the projections generated will be acceptable. But what is meant by ‘acceptable’?

Acceptability

A model which forecasts sales may well be delegated to a sales or marketing function, within an organisation, but developing and verifying a model are usually only the first steps in a process to get the forecasts accepted.

Depending on the size of a company, a model will normally require input from other functional areas of the business such as operations, purchasing, finance and so on; although marketing may take the lead in developing a model, the co-operation of other functions is often essential.

Once the model has been completed, the next stage of the process is to submit the model to a CEO or Board of Directors for their approval. It is unlikely that model itself would be considered in detail at such a high level of the company, so a model also needs documentation. A recent model I developed contained 85 separate sheets in an Excel file and Figure 1-3 provides a summary of how the model works, from inputs, via calculations, to outputs.

Figure 1-3: Model Flow Diagram

This flow diagram is part of a 70-page, 14,000-word document called the ‘Record of Assumptions’ (RoA). As the name suggests, the RoA contains the assumptions used in developing the model and forecasts but also a user guide to explain how the model can be used as well as key outputs from the model. Documenting the model can be viewed as being as important as developing the model itself, since the documentation acts as a tool to persuade and convince stakeholders to sign on to the forecasting process proposed.

---

¹ Strengths, Weaknesses, Opportunities and Threats

2. ACME FOOD STORES PLC

Introduction

A fictional company is used as a running example throughout the book, because management accounts and internal data are more effective in developing forecasts than the use of published financial information alone. As such accounts are rarely published (and it would be inappropriate to expose a company’s private data to public scrutiny), it was simpler to develop a fictional, but plausible, set of such accounts to illustrate many of the issues and techniques highlighted in this book.

Acme Food Stores plc (hereafter referred to as Acme) is presented as a medium-sized supermarket chain with around 500 stores in the UK. It has a small market share, fluctuating between 0.5% and 1% of total sales in the UK. The company owns all its retail outlets. All the figures quoted in this chapter are based on 2018 sterling (£) rates, unless otherwise stated.

The Food Store Sector in the UK

Overall Growth

Acme operates in the retail food (grocery) sector, which is currently worth around £160 billion of sales per annum. The profile of sales for the sector from 2000 to 2018 is shown in Figure 2-4.

Figure 2-4: Quarterly Sales (in £m 2018), Retail Food Sector

Source:https://www.ons.gov.uk/businessindustryandtrade/retailindustry/datasets/retailsalesindexreferencetables and author’s calculations

The sector appears to have been in a state of steady growth for the first seven years, followed by significant growth from 2013 onwards. In the intervening years (2008-2012), sales stalled as the global recession hit in 2008. By 2018, sales appeared to have returned to the peak levels seen in 2006.

Market Shares

Although the market has grown somewhat since 2012, the shares of rival companies have shown significant changes. Figure 2-5 shows market shares for the major chains in 2012 and 2018.

Figure 2-5: Food Chains' Market Shares (%)

Source: https://www.statista.com/statistics/300656/grocery-market-share-in-great-britain-year-on-year-comparison/ , author’s calculations

The largest four chains have all suffered a drop since 2012 and their combined market share has dropped almost 8 percentage points.

Almost all of the losses incurred by the Big Four have been gained by the two discounters, Aldi and Lidl (up 7.5%). There has been barely any change in the share of independents such as Acme.

Stores and Revenue per Outlet

In 2000, Acme had 530 stores across the UK, with the average store size being around 1,000 m² (so similar in size to Tesco Metro). However, poor performance saw the closure of some of the weaker performing outlets as the revenue per store fell, as shown in Figure 2-6.¹

Figure 2-6: Revenue per store and number of stores

As revenue per store fell in 2009 and 2010, the key criterion for closure, other than weak performance, was proximity to other outlets wherever possible. As a result, sales per store started to increase again in 2014. However, even by 2018, with the weakly performing stores now closed, average revenue per store was still less, in real terms, than in 2007. To provide some context regarding Acme’s competitiveness, the company’s reach is relatively limited compared to the leading supermarket brands, as demonstrated in Figure 2-7.

Figure 2-7: Number of Stores (February 2018)

Source: https://www.statista.com/statistics/920074/number-of-stores-of-supermarkets-united-kingdom-uk/ by Nils-Gerrit Wunsch, Jan 30, 2019

Financial Performance in Detail

Acme has undergone periods of boom and recession since 2000; its annual performance is presented in Figure 2-8.

Figure 2-8: Acme Revenue (in £m 2018)

A more useful way to assess Acme’s performance, however, is to use the relationship of revenue being the sum of costs and operating profit, as in Figure 2-9.

Figure 2-9: Acme Financial Performance 2000-2018 (in £m 2018)

Figure 2-9 should be read as follows. Revenue for Acme comprises four elements in these simplified accounts:

Staff costs

Cost of goods sold

Energy and other utilities and

Operating profit².

Figure 2-9 figure highlights the fact that operating profit in recent years has been significantly lower than in the previous decade, when energy costs were somewhat lower.

Up to 2008, Acme recorded a positive net operating profit, but profitability was negligible or negative for the next four years. Acme has since recovered; in real terms, in 2016, Acme recorded a further positive operating profit but suffered a small setback in 2017 as the cost of goods sold increased due to a drop in the exchange rate after the Brexit referendum (Figure 2-10).

Figure 2-10: Acme Operating Profit (£m 2018)

A final means of assessing financial performance is to examine operating margin. Figure 2-11 shows that operating profit per £ of revenue is significantly lower than in the previous decade.

Figure 2-11: ACME Operating Margin (%)

In the decade up to 2010, Acme’s operating margin was higher than average as the average store acted as a hybrid between a supermarket and a convenience store.

From 2004 onwards, though, competition in this sub-sector heated up, causing margins to decline and, combined with the 2008-2010 recession, led to the company’s first operating loss in 2009. The operating margin for Tesco in the year up to February 2019 was 6.6%, so Acme ‘s figure is similar to the market leader.

Employees

The number of staff employed by Acme now stands at a little over 6,000, a figure which is considerably lower than at the beginning of the century, when over 7,000 people were on Acme’s payroll.

Figure 2-12: Number of Employees

The retrenchment took place up to 2006 and staff numbers have been relatively constant since then. The objective of the exercise was to increase employee productivity; in terms of goods sold per employee, the results of this exercise can be seen in Figure 2-13.

Figure 2-13: Sales per Employee (2018 £)

The exercise was clearly successful up to 2007 but productivity suffered a precipitate decline until 2010. The number of employees was considered to have been cut as much as possible without damaging the quality of customer service and Acme made a decision not to reduce the number of staff any further, preferring to ride out the recession and still have sufficient resources available for when the UK economy recovered.

Additional Issues for Acme

In Store Operations – Self Scan

Self-scan operation with grocery stores can vary significantly, from trialling the process at selected stores to implementation of a (nearly) fully automated checkout system. Acme has been slower than most of its competitors at installing self-scan devices due to concerns from customers and staff as well as the potential for increased rates of theft. However, Acme considers that, in spite of the high installation costs, the benefits of greater customer choice and satisfaction, along with higher employee satisfaction acquired by moving away from the monotony of till work, will outweigh the costs.

Online Sales

Although online sales accounted for around 5% of total grocery sales in 2018, Acme has also been somewhat of a laggard in this area, with barely 1% of its revenue attributable to online sales. Not only was it late in developing an online strategy but online shopping is only available in certain areas of the country and its website has received poor reviews for ease of use. Acme’s top management is aware of its deficiencies in this area and is currently developing a major overhaul of its current online operations to compete more effectively in this area.

Suppliers

At present, Acme acquires its goods from a highly competitive network of suppliers in the UK and the rest of Europe. However, management is concerned that Brexit will reduce supplier competitiveness and also expects tariffs to increase the overall costs of goods sold. Although Acme is expected to absorb some of the price increases, the bulk will need to be passed on to the consumer.

---

¹ Raw data for Acme is available at http://art-and-science-of-forecasting.com/downloads/

² as Revenue – Costs = Operating Profit, just add costs to both sides of the equation

3. ARE FORECASTING ERRORS INEVITABLE?

Chapter Overview

This chapter examines various forecasting errors. Optimism bias and technical errors are very much the responsibility of the personnel responsible for forecasting and therefore can be considered avoidable. However, many types of inaccurate forecast are the result of changes in the macro-environment which would test the capabilities of any forecaster and we will briefly assess these external factors later, in this chapter.

Systemic Errors

In the past five years ECB forecasts have proven to be systematically incorrect: core inflation remained broadly stable at 1% despite the stubbornly predicted increase, while the unemployment rate fell faster than predicted. Such forecast errors […] raise serious doubts about the reliability of the ECB’s current forecast of accelerating core inflation and necessitates a reflection on the inflation aim of the ECB

The extract is from a 2018 article highlighting forecasting errors at the European Central Bank (ECB)¹.. The article could be viewed as somewhat harsh. The ECB covers 19 countries, each with its own factors influencing unemployment and inflation and their forecasts cover a period of 2½-3 years. The Euro-wide forecasts are developed not just by the ECB but also the national banks of each Member State using the Euro and it is unlikely that each national bank has access to the same quality of data and personnel necessary for accurate forecasting. It is therefore fair to suggest that some streams of data are easier to forecast than others. However, technical difficulties in forecasting can be compounded by ‘man-made’ errors and we will look at these next.

Technical Errors

An example of a technical error in which the forecasting model produced was not fit for purpose is presented here. When developing a forecasting model, a commonplace check is to ensure how well the model fits historical data. In this example, we will concentrate on residuals which are defined as:

Residual X = Actual X – Modelled X

where X is a given month, quarter or year. The objective here is to ensure that the residuals are as low as possible and that the forecast values do not drift away from the actual values. To illustrate this point, here are four years of historical data. Examine how the two distinct forecasting models fit this data. The results are shown in Figure 3-14.

.Figure 3-14: Residuals for Four Sample Years

The residuals for model 1 are stable and move at random on either side of zero. In contrast, the residuals for model 2 are increasing over time which are a source of concern. If the selection is expanded and we look at two charts from a different example plotting 67 historical values in increasing order of size with their residuals, the problem is clearer. For ease of comparison, Figure 3-15 and Figure 3-16 use the same scale.

Figure 3-15: Low and Stable Residuals