ITGS Syllabus

Friday, May 04, 2007

Topic 216

Forecasting by Ronald Chu

The basic definition of forecasting in technological terms is “forecasting the future characteristics of useful technological machines, procedures or techniques.” Forecasting is the process of estimation in unknown situations. It is similar to the word “prediction” but is more general and used in the discussion of time-series data. There are two main aspects of technological forecasting. Primarily, a technological forecast deals with the characteristics of technology, such as levels of technical performance, like speed of a military aircraft, the power in watts of a particular future engine, the accuracy or precision of a measuring instrument, the number of transistors in a chip in the year 2015, etc. Secondly, technological forecasting usually deals with only useful machines, procedures or techniques. This is to exclude commodities, services or techniques intended for luxury or amusement.

There are no real alternatives to technological forecasting. If a decision-maker has several alternatives open to him, he will choose the basis of which provides him the most desirable outcome. His only choice is whether the forecast is obtained by rational and explicit methods, or by intuitive means. There are four guidelines that must be followed when using rational methods. First of all, they can be taught and learned. Second of all, they can be described and explained. Thirdly, they provide a procedure possible to be followed by anyone who has gone through the necessary training. Finally, these methods are even guaranteed to produce the same forecast regardless of who uses them.

There are many methods of technological forecasting. They are the Delphi method, forecast by analogy, growth curves and extrapolation. Normative methods of technology forecasting — like the relevance trees, morphological models, and mission flow diagrams — are also commonly used. The Delphi technique is a method for obtaining forecasts from a panel of independent experts over two or more rounds. Here, experts are asked to predict quantities. In mathematics, extrapolation is the process of constructing new data points outside a discrete set of known data points. It is similar to the process of interpolation, which constructs new points between known points, but its results are often less meaningful, and are subject to greater uncertainty.

Although there are no “real” alternatives to technological forecasting, there are some exceptions. First of all, there can be no forecast at all. This means that we do not predict the future at all and just let things be. When something happens, it happens; we may or may not be prepared for it. Then, there is the “anything can happen” attitude. Similar to the first alternative, we do nothing to predict the future. This represents the attitude that the future is a complete gamble, that nothing can be done to influence it in a desired direction, and that there is no point therefore in attempting to anticipate it. Thirdly, there is the “glorious past” attitude. This is a bit different from the other two. This represents an attitude which looks to the past and ignores the future. Many organizations can point to significant achievements at some time or other in the past.

However, this attitude leads to the road of disaster. Fourthly, there is the window-blind forecasting alternative. This involves the attitude that technology moves on a fixed track, like an old-fashioned roller window blind and that the only direction is up. While this attitude does at least recognize that changes do take place and is therefore somewhat better than the other alternatives, it fails to recognize that there are other directions besides up. However, an organization that depends on window-blind forecasting will be taken by surprise, as some unexpected technological change will hit them hard. Finally, there is the genius forecasting alternative. This method consists in finding a genius, and asking him for his intuitive forecast. Many of these genius forecasts made in the past have been very successful. Unfortunately, there have also been many so wide of the mark as to be useless. In conclusion, it should be clear that where rational and explicit methods are available, they are much to be preferred.


Forecasting by Romeo Wu

Forecasting is the process of estimation in unknown situations. Prediction is a similar, but more general term, and usually refers to estimation of time series, cross-sectional or longitudinal data. In more recent years, Forecasting has evolved into the practice of Demand Planning in every day business forecasting for manufacturing companies. The discipline of demand planning, also sometimes referred to as supply chain forecasting, embraces both statistical forecasting and consensus process.

Weather forecasting is a prediction of what the weather will be like in an hour, tomorrow, or next week. The people who study the weather and make forecasts are called meteorologists. Meteorologists use special, high-tech equipment to help them make their forecasts. But you can make forecasts by watching clouds or feeling the blowing wind. To learn how, read through the Forecasting lesson, and get ready to go camping.

There are several different methods that can be used to create a forecast. The method a forecaster chooses depends upon the experience of the forecaster, the amount of information available to the forecaster, the level of difficulty that the forecast situation presents, and the degree of accuracy or confidence needed in the forecast.

The first of these methods is the Persistence Method; the simplest way of producing a forecast. The persistence method assumes that the conditions at the time of the forecast will not change. For example, if it is sunny and 87 degrees today, the persistence method predicts that it will be sunny and 87 degrees tomorrow. If two inches of rain fell today, the persistence method would predict two inches of rain for tomorrow.

The persistence method works well when weather patterns change very little and features on the weather maps move very slowly. It also works well in places like southern California, where summertime weather conditions vary little from day to day.

However, if weather conditions change significantly from day to day, the persistence method usually breaks down and is not the best forecasting method to use. It may also appear that the persistence method would work only for shorter-term forecasts (e.g. a forecast for a day or two), but actually one of the most useful roles of the persistence forecast is predicting long range weather conditions or making climate forecasts. For example, it is often the case that one hot and dry month will be followed by another hot and dry month.

So, making persistence forecasts for monthly and seasonal weather conditions can have some skill. Some of the other forecasting methods, such as numerical weather prediction, lose all their skill for forecasts longer than 10 days. This makes persistence a "hard to beat" method for forecasting longer time periods.


Post a Comment

<< Home