A forecast, at the business level, is the prediction of what will happen to a given item within a given set of conditions. It differs from the budget because the latter is the result of decisions aimed at generating the conditions that will promote a desired level of said element.
Why forecasts are needed in the company
The basic objective of a forecast is to reduce the range of uncertainty within which decisions are made that affect the future of the business and with it all parties involved. Although the forecast is not a substitute for administrative judgment in decision making, it is simply an aid in that process.
Forecasts are used in the process of establishing both long-term and short-term objectives, thus becoming the basis for the development of plans, at a general level and in the different areas or units. The plans based on these forecasts will not only attend to them but will establish strategies and actions that can counteract, correct or promote them.
For example, if the sales forecast for the following fiscal year shows an unfavorable trend, then the strategic sales plan should be aimed at reversing this trend through actions that promote growth or that do not allow sales to decline or, on the worst case, they are simply reduced to a minimum level.
Uses of forecasts in the company
All organizations that plan the conditions of their future, which they do not know for sure, use forecasts in their different functional areas. Some use cases of forecasts in the company are:
- In the marketing area, it is predicted how the market will grow, what will be the own participation and that of the competitors, what will be the price trend, what will be the new products that will shake the market… In the production area they are made forecasts on the cost and availability of raw material, the cost and availability of labor, when the equipment will require maintenance, what will be the plant capacity necessary to meet the demand… In the financial area, it is forecast which will be the reference interest rate for loans, what will be the level of uncollectible accounts, how much capital will be required to expand own capacity… In human resources, forecasts are required on the number of workers, staff turnover, absenteeism trends,training needs… At the strategic level, forecasts are made about economic factors, price changes, costs, growth of product lines…
Features of the business forecast
- It is consistent with the other areas of the business. If marketing predicted a 25% growth in units sold then production and human resources must be able to deliver. It is based on adequate knowledge of the relevant past. Although there are exceptions, the rule is that behaviors that occurred in the past are a source of prediction for the future. It takes into account the political and economic environment. A change in the conditions of these factors can have enormous consequences in any economic sector. It is timely. Whether it's to gain market share by introducing a new product or to retire another and avoid a crisis, the most accurate forecast loses all its usefulness if the right opportunity to apply it in planning has been missed.
Classification of forecasting models
According to the time frame they serve, they are classified into:
- Short term. They are used to design immediate strategies, they are used among middle managers and first line managers. Medium term. Together in the short and long term, useful for decisions at all levels. Long-term forecasts. Required to set the overall direction of the organization, they are generally made for use by top management in strategic planning processes.
According to their attention to detail they are classified into:
- Micro- diagnostics. They involve small details and interest the middle and frontline levels. Macropus ronósticos. They are carried out on a large scale and are in the interest of top management.
According to the intensity of data use, they are classified into:
- Qualitative forecasts. They are based on the judgment of individuals or groups of individuals, they can be presented in numerical form but are generally not based on historical data series. Quantitative forecasts. They use significant amounts of prior data as a basis for prediction. They may be:
- Simple (non-formal): project past data into the future without explaining future trends Causal (explanatory): attempt to explain the functional relationships between the variable to be estimated (dependent variable) and the variable or variables that explain the changes (independent variables).
Qualitative methods
Qualitative techniques are used when data is scarce, for example when a new product is introduced to the market. These techniques use the judgment of the person and certain relationships to transform qualitative information into quantitative estimates. Some are:
- Executive opinion jury. A group of corporate executives meet, their opinions are averaged to generate the forecast. Composition of the sales force. Combine vendor estimates of expected customer purchases. Delphi method. Used predominantly in the prediction of trends and technological changes. It employs a panel of experts who do not meet but rather the process is carried out through a sequential series of written questions and answers. Opinion polls. They allow to identify changes in trends, they are carried out in samples of the population. Market research. It is used to evaluate and test hypotheses about real markets.Customer evaluation. Combine estimates from regular customers.
The following video, from the UPV, presents the characteristics of four of the qualitative methods most used in forecasting.
Quantitative methods
They are based on mechanical procedures or mathematical models that rely on historical data or causal variables to produce quantitative results. Some are:
- Time series analysis. Establish an equation for a trend and project it into the future Regression models. Forecasts one variable based on what is known or assumed about others. Econometric models. Simulate segments of the economy with regression equations. Economic indicators. Forecast with one or more indicators the future state of the economy Substitution effect. Predict with a mathematical formula how, when and under what circumstances a new product or technology will replace the current one.
Through the following video tutorial (8 videos), from INCAE, you can learn more about quantitative forecasting methods.
How to choose the right forecasting method
The main consideration for selecting a forecasting method is that its results should guide, in the best way, administrative decision-making, otherwise, the use of any method, no matter how sophisticated, will not be convenient. Some of the variables to consider when selecting the most appropriate forecasting technique or method are:
- The context of the forecast The relevance and availability of historical data The degree of accuracy desired The period of time to be forecast The cost-benefit analysis of the forecast The point of the life cycle of the product.
Some of the questions to ask before deciding on the most appropriate forecasting technique for a specific problem include the following:
- Why is a forecast needed? Who will use the forecast? What are the characteristics of the available data? What period should be forecast? What are the minimum data requirements? How accurate is desired? How much will the forecast cost? forecast?
In order to properly select the appropriate forecasting technique, the forecaster must be able to:
- Define the nature of the forecasting problem Explain the nature of the data being investigated Describe the capabilities and limitations of potentially useful forecasting techniques Develop some predetermined criteria upon which the selection decision can be made
An important factor influencing the selection of a forecasting technique is identifying and understanding historical patterns in the data. If trend, cyclical or seasonal patterns can be recognized, techniques capable of extrapolating them effectively can be selected.
The forecasting process
Generally, a forecast is made by following the steps listed below:
- Formulation of the problem and data collection. These two items are treated as a single step because the problem determines the appropriate data. If adequate data are not available, the problem would have to be redefined or a purely qualitative method would have to be used. Manipulation and cleaning of data. It is possible to have too much or little data, irrelevant data, outdated data, etc., all of them will require some processing to obtain the necessary and adequate data. Construction and evaluation of the model. It involves using the data in a forecasting model that is adequate in terms of minimizing forecast error. Application of the model (the actual forecast). It consists of the actual model forecasts that are generated once they have been collected and perhaps reduced to just the right data, as soon as a suitable forecasting model has been chosen. Prognosis evaluation. It involves comparing the forecast values with the actual historical values. Examining patterns of errors often leads the analyst to modify the forecasting procedure.
Bibliography
- Hanke, John E. and Wichern, Dean W. Forecasts in business. Pearson Education, 2006, pp. 1-13Keat, Paul G. and Young, Philip KY Business Economics. Pearson Education, 2004, pp. 221-269 Robbins, Stephen P. Administration. Pearson Education, 2005, p.209.
