BUSINESS FORECASTING is an estimate or prediction of future developments in business such as sales, expenditures, and profits. Given the wide swings in economic activity and the drastic effects these fluctuations can have on profit margins, it is not surprising that business forecasting has emerged as one of the most important aspects of corporate planning. Forecasting has become an invaluable tool for businesspeople to anticipate economic trends and prepare themselves either to benefit from or to counteract them. If, for instance, businesspeople envision an economic downturn, they can cut back on their inventories, production quotas, and hirings. If, on the contrary, an economic boom seems probable, those same businesspeople can take necessary measures to attain the maximum benefit from it. Good business forecasts can help business owners and managers adapt to a changing economy.
At a minimum, businesses now need annual forecasts. One reason business planners prefer the annual averages is that sudden changes in the economic climate can play havoc with the quarter-to-quarter measurements. For instance, during the first half of 1984, a sudden growth spurt in the economy upset most business forecasts. Spurred to expansiveness by a surging cash flow, businesses added to their stock of plant and equipment at the fastest rate in five years. Government spending also went up faster than expected, as did business inventories. That set the stage for the sharp second-half slowdown that included an increased demand for credit and, consequently, higher interest rates. At the time, few had foreseen the short-term trend.
Many experts agree that precise business forecasting is as much an art as a science. Because business cycles are not repetitious, a good forecast results as much from experience, sound instincts, and good judgement as from an established formula. Business forecasters can be, and have often been, completely off the mark in their predictions. If nothing else, business forecasts can be used as blueprint to better understand the nature and causes of economic fluctuations.
Creating the Business Forecast
When twentieth-century business forecasting began, economists looked at a variety of factors, from money to boxcar holdings to steel production. Sometimes the factors were added together to create an index of leading economic indicators that acted as a barometer of future economic conditions.
Modern forecasting got its impetus from the Great Depression of the 1930s. The effort to understand and correct the worldwide economic disaster led to the development of a vastly greater compilation of statistics as well as the evolution of techniques needed to analyze them. Business organizations manifested more concern with anticipating the future, and a number of highly successful consulting firms emerged to provide forecasting help for governments and businesses.
Forecasting for a business begins with a survey of the industry or industries in which it is involved. Beyond that initial review, the analyst determines the degree to which the company's share of each market may vary during the forecasting period. Today, business forecasting is done with the help of computers and special programs designed to model the economic future. Many of these programs are based on macroeconomic models, particularly those of Lawrence Klein of the Wharton School of Business, winner of the 1980 Nobel Prize for his work in economic modeling. Over a period of thirty years, Klein constructed a number of forecasting systems. Two of these systems, the econometric unit of the Chase Manhattan Bank and the Data Resources Inc. (DRI) model, are among the most widely used forecasting programs.
Forecasting programs are often put together and run as a system of mathematical equations. Early models were composed of a dozen or more different equations. The larger systems of today, however, have anywhere from a few hundred to approximately 10,000 variables that can be used to create a forecast. Forecasters also examine certain external variables such as population, government spending, taxation, and monetary policy to calculate how each will influence future trends and developments. They may conduct a "naive forecast" in which they assume that the next year's rate of growth will be equal to the growth rate of the present year. Taking these factors into account, forecasters create their model to provide a business fore-cast for the following week, month, year, or decade.
Numerical forecasts of the main national accounts, national economic indicators, industry time series, and firm accounting statements are regularly prepared. The forecasting of business trends takes place on three levels: at the national level, at the industry or market level, and at the level of the individual firm. It has become popular to combine forecasts for one, two, or three years ahead and to include quarterly forecasts spanning the same time horizon. Some firms need monthly or weekly forecasts, whereas others use forecasts that look forward two or three decades in order to make their decisions. Among the companies that commonly use long-range forecasting are life insurance corporations, public utility companies, and firms involved in long-term construction or manufacturing projects.
The Accuracy of Business Forecasts
Although businesses and governments pay millions of dollars for forecasts, those forecasts are not always on target, particularly during turbulent economic times. Perhaps one of the worst years on record for business fore-casters was 1982. Experts generally believe that business forecasters, caught up in the excitement of President Reagan's supply-side economic programs, simply stopped paying attention to what was really happening. As a result, the 1982 forecasts are among the worst in economic history.
Making accurate business forecasts is most difficult for companies that produce durable goods such as automobiles or appliances, as well as for companies that supply the basic materials to these industries. Problems arise because sales of such goods are subject to extreme variations. During the early 1970s, annual sales of automobiles in the United States increased by 22 percent in one year and declined by 22.5 percent in another. Consequently, the durable goods industries in general, and automobile companies in particular, have developed especially complex and sophisticated forecasting techniques. In addition to careful analysis of income trends (based on a general economic forecast), automobile companies, which are acutely sensitive to competition from imports, underwrite a number of studies of consumer attitudes and surveys of intentions to purchase automobiles.
The Future of Business Forecasting
Today, many executives are unhappy with the economic forecasts they receive. As a result, they have fired economists and are paying less attention to macroeconomic forecasts, arguing that these forecasts cost too much and reveal too little. Instead they are now leaning more heavily on their own rough-and-ready indicators of what is likely to happen to their businesses and industries. When they do consult economists, they increasingly send them into the field with line managers to forecast the particulars that really matter.
Executives are now exploring other means of fore-casting the business future. Some watch the growth of the Gross National Product (GNP). Disposable personal income is another broad measure that suffices, particularly in retailing. By observing whether economic indicators rise or fall, executives can more accurately predict their retail sales picture in six months or a year.
For many companies, however, no single indicator works to predict the future. Some might use the monthly consumer confidence index or study the stock market with regard to certain companies. Depending on the circumstances, interest rates may have a bearing on the future. High or low rates may determine whether the consumer will be in the market to buy or just keep looking at certain products such as cars, boats, houses, and other big-ticket items. Many companies are taking one or more basic indicators and building them into economic models tailor-made for specific industries and markets.
Scenario Planning versus Business Forecasting
In the 1990s, economists developed new methods of business forecasting that rest more on hard data and less on theoretical assumptions. They acknowledge that the economy is dynamic and volatile, and have tried to keep in mind that all forecasts, however sophisticated, are greatly simplified representations of reality that will likely be incorrect in some respects.
One of the newer forecasting techniques is called "scenario forecasting." More businesses are using the scenario method to devise their "strategic direction." In scenario forecasting, companies develop scenarios to identify major changes that could happen in the world and determine the possible effects those changes will have on their operations. They then map out ways in which to react if those occurrences come to pass, hoping that the hypothetical exercise will make them better prepared to take action when a real economic crisis takes place.
One of the biggest reasons to use the scenario method is that traditional forecasting does not keep up with the lightning-quick pace at which modern business moves. Where change could once be anticipated over a period of time, the advent of sophisticated technology, which by itself is ever changing, has shown businesspeople that they need a new way of looking at and thinking about the economic future.
Fost, Dan, and Brad Edmonston. "How to Think about the Future." American Demographics 20 (February 1998): 6–12.
Gunther, Robert E., and Paul J.H. Schoemaker. Profiting from Uncertainty: Strategies for Succeeding No Matter What the Future Brings. New York: Free Press, 2002.
Hutchins, Dexter. "And Now, the Home-Brewed Forecast." Fortune, 20 January 1986, 53–54.
Pindyck, Robert S., and Daniel L. Rubinfield. Econometric Models and Economic Forecasts. Boston: McGraw Hill, 1998.
Business forecasting has always been one component of running an enterprise. However, forecasting traditionally was based less on concrete and comprehensive data than on face-to-face meetings and common sense. In recent years, business forecasting has developed into a much more scientific endeavor, with a host of theories, methods, and techniques designed for forecasting certain types of data. The development of information technologies and the Internet propelled this development into overdrive, as companies not only adopted such technologies into their business practices, but into forecasting schemes as well. In the 2000s, projecting the optimal levels of goods to buy or products to produce involved sophisticated software and electronic networks that incorporate mounds of data and advanced mathematical algorithms tailored to a company's particular market conditions and line of business.
Business forecasting involves a wide range of tools, including simple electronic spreadsheets, enterprise resource planning (ERP) and electronic data interchange (EDI) networks, advanced supply chain management systems, and other Web-enabled technologies. The practice attempts to pinpoint key factors in business production and extrapolate from given data sets to produce accurate projections for future costs, revenues, and opportunities. This normally is done with an eye toward adjusting current and near-future business practices to take maximum advantage of expectations.
In the Internet age, the field of business forecasting was propelled by three interrelated phenomena. First, the Internet provided a new series of tools to aid the science of business forecasting. Second, business forecasting had to take the Internet itself into account in trying to construct viable models and make predictions. Finally, the Internet fostered vastly accelerated transformations in all areas of business that made the job of business forecasters that much more exacting. By the 2000s, as the Internet and its myriad functions highlighted the central importance of information in economic activity, more and more companies came to recognize the value, and often the necessity, of business forecasting techniques and systems.
Business forecasting is indeed big business, with companies investing tremendous resources in systems, time, and employees aimed at bringing useful projections into the planning process. According to a survey by the Hudson, Ohio-based AnswerThink Consulting Group, which specializes in studies of business planning, the average U.S. company spends more than 25,000 person-days on business forecasting and related activities for every billion dollars of revenue.
Companies have a vast array of business forecasting systems and software from which to choose, but choosing the correct one for their particular needs requires a good deal of investigation. According to the Journal of Business Forecasting Methods & Systems, any forecasting system needs to be able to facilitate data-sharing partnerships between businesses, accept input from several different data sources and platforms, operate on an open architecture, and feature an array of analysis techniques and approaches.
Forecasting systems draw on several sources for their forecasting input, including databases, e-mails, documents, and Web sites. After processing data from various sources, sophisticated forecasting systems integrate all the necessary data into a single spreadsheet, which the company can then manipulate by entering in various projections—such as different estimates of future sales—that the system will incorporate into a new readout.
A flexible and sound architecture is crucial, particularly in the fast-paced, rapidly developing Internet economy. If a system's base is rigid or inadequate, it can be impossible to reconfigure to adjust to changing market conditions. Along the same lines, according to the Journal of Business Forecasting Methods & Systems, it's important to invest in systems that will remain useful over the long term, weathering alterations in the business climate.
One of the distinguishing characteristics of forecasting systems is the mathematical algorithms they use to take various factors into account. For example, most forecasting systems arrange relevant data into hierarchies, such as a consumer hierarchy, a supply hierarchy, a geography hierarchy, and so on. To return a useful forecast, the system can't simply allocate down each hierarchy separately, but must account for the ways in which those dimensions interact with each other. Moreover, the degree of this interaction varies according to the type of business in which a company is engaged. Thus, businesses need to fine-tune their allocation algorithms in order to receive useful forecasts.
According to the Journal of Business Forecasting Methods & Systems, there are three models of business forecasting systems. In the time-series model, data simply is projected forward based on an established method—of which there are several, including the moving average, the simple average, exponential smoothing, decomposition, and Box-Jenkins. Each of these methods applies various formulas to the same basic premise: data patterns from the recent past will continue more or less unabated into the future. To conduct a forecast using the time-series model, one need only plug available historical data into the formulas established by one or more of the above methods. Obviously, the time-series model is the most useful means for forecasting when the relevant historical data reveals smooth and stable patterns. Where jumps and anomalies do occur, the time-series model may still be useful, providing those jumps can be accounted for.
The second forecasting model is cause-and-effect. In this model, one assumes a cause, or driver of activity, that determines an outcome. For instance, a company may assume that, for a particular data set, the cause is an investment in information technology, and the effect is sales. This model requires the historical data not only of the factor with which one is concerned (in this case, sales), but also of that factor's determined cause (here, information technology expenditures). It is assumed, of course, that the cause-and-effect relationship is relatively stable and easily quantifiable.
The third primary forecasting model is known as the judgmental model. In this case, one attempts to produce a forecast where there is no useful historical data. A company might choose to use the judgmental model when it attempts to project sales for a brand new product, or when market conditions have qualitatively changed, rendering previous data obsolete. In addition, according to the Journal of Business Forecasting Methods & Systems, this model is useful when the bulk of sales derives only from a relative handful of customers. To proceed in the absence of historical data, alternative data is collected by way of experts in the field, prospective customers, trade groups, business partners, or any other relevant source of information.
Business forecasting systems often work hand-in-hand with supply chain management systems. In such systems, all partners in the supply chain can electronically oversee all movement of components within that supply chain and gear the chain toward maximum efficiency. The Internet has proven to be a panacea in this field, and business forecasting systems allow partners to project the optimal flow of components into the future so that companies can try to meet optimal levels rather than continually catch up to them.
In integrated supply chain networks, for instance, a single company in the supply chain can enter slight changes in their own production or purchasing schedules for all parties to see, and the forecasting system immediately processes the effects of those changes through the entire supply chain, allowing each company to adjust their own schedules accordingly. With business relationships and supply chains growing increasingly complex—particularly in the world of e-commerce, with heavy reliance on logistics outsourcing and just-in-time delivery—such forecasting systems become crucial for companies and networks to remain efficient.
Allen, David. "Looking Forwards." Management Accounting. March 2000.
Culberston, Scott; Jim Burruss; and Lee Buddress. "Control System Approach to E-commerce Fulfillment." Journal of Business Forecasting Methods & Systems. Winter 2000/2001.
Jain, Chaman L. "Which Forecasting Model Should We Use?" Journal of Business Forecasting Methods & Systems. Fall 2000.
Lapide, Larry. "New Developments in Business Forecasting: The Internet Does Not Eliminate the Need to Forecast." Journal of Business Forecasting Methods & Systems. Fall 2000.
McKeefry, Hailey Lynne. "Adding More Science to the Art of Forecasting." Ebn. March 5, 2001.
Safavi, Alex. "Choosing the Right Forecasting Software and System." Journal of Business Forecasting Methods & Systems. Fall 2000.
"Squeeze the Process." CMA Management. Oct 1999.
SEE ALSO: Data Mining; Electronic Data Interchange (EDI); Enterprise Resource Planning (ERP); Forecasting, Technological; Scenario Planning; Simulation Software; Supply Chain Management