Table of Contents
Need Of Forecast In Production /operations Management
There are two basic reasons for the need for the forecast in any field more so in production/ operation management.
1) Purpose –
Any action/plan is contemplated/devised in the PRESENT to take care of some contingency accruing out-of a situation/condition or set of conditions set in the future. These future conditions offer a purpose/target to be achieved so as to take advantage of or to minimize the impact of (if the foreseen conditions are adverse in nature) these fixture conditions. An action or a plan can not be taken/devised in void-without any purpose/objective/target. Any plan of action is to achieve something This`something’ is a derived function of future condition (s).
Example:
The action/plan to set up an additional plant to increase production capacity. How much increased production and what should be the size of the new plant is dependent on the future demand-supply gap. To take advantage of this future demand-supply gap, a target of increased production is arrived at. To achieve this target a plan is prepared and put into action.
2) Time –
To prepare a plan, organize resources for its implementation, implement; and complete the plan; all these need time as a resource. Some situations need very little time; some other situations need several years of time. Therefore, the future forecast is available in advance, appropriate actions can be planned and implemented ‘in time’.
Example: Consider the same example discussed earlier -to take advantage of a future demand-supply gap; a)
General Steps In The Forecasting process
The general steps in the forecasting process are as follows:
1)Indentify the General Need.
For example: in the present manufacturing business, unfulfilled demand might have been observed. The manufacturer mayhave a feeling, “Why not expand production?” This should constitute theindentification of general need. Still, the manufacturer does not know for certainwhether expansion is really a wise decision? How much to expand? When toexpand?
2)Select the Period(Time Horizon) of Forecast:
Considering the same example:General estimate regarding time taken to errect the plant. And beyond that theusual plant life. Thus, in this case long term forecast is needed. The long term’can be defined appropriately for each situation. In this case, if we consider timefor plant errection to be roughly 3 years-then we need a forecast spanning 5-10years beyond 3 years. That means a forecast covering a period of 5 years startingthree years from now.
3)Select the Indicators Relevant to the Need:
Depending upon the product or product line, one or more of the following may be identified:
i) Industry Sales
ii) Competitors (collective) present and projected capacity.
iii). Population projection (in case product is directly related to the population)
iv) Income levels
v) Economic development etc.
4)Select the Forecast Model to be Used:
For this, knowledge of variousforecasting models, in which situations these are applicable, how reliable eachone of them is what type of data is required. On these considerations; one ormore models can be
5)Data Collection:
with reference to various indicators identified –collect datafrom various appropriate sources –data which is compatible with the model(s)selected in steps(4).Data should also go back that much in past , which meetsthe requirements of the model.
6) Prepare Forecaste:
Apply the model using the data collected the value of the forecast.
7)Evaluate:
The forecast obtained through any of the models should not be used, as it is, blindly. It should be evaluated in terms of ‘confidence interval’ –usually, all good forecast models have methods of calculating upper value within which the given forecast is expected to remain with a certain specified level of probability. It can also be evaluated from a logical point of view whether the value obtained in logically feasible? It can also be evaluated against some related variables or phenomena. Thus, it is possible, some times advisable to modify the statistically forecasted’ value based on the evaluation.
Importance And Applications of forecasts In Production/operations Management
The importance of forecast lies in its ability to help the managers /planners to help them make better actions regarding the future and also to help them in discharging their functions more effectively. How does it help?
A manager invariably continues to discharge his functions-forecast or no forecast. When a forecast is available:
1) The manager is comparatively better informed so as to set up his objectives more clearly.
2)His thinking and generation and choice of alternatives become more focused.
3) Because sufficient time is available, it is possible to organize and implement his actions in a more effective way.
The importance is directly proportional to:
[Results of action based on forecast] -[Results of action for the same situation without any forecast].
If the difference is positive and large then the importance is more, otherwise, it is not important.
The importance of forecast and of the ability to used statistical forecasting techniques to generate reliable/accurate forecasts are directly related. If in general forecasts are not accurate i.e. quantum of forecast error is more; then a difference of results of actions as discussed above may not be relevant. Because both become unreliable.
Forecast Error can be explained as:
Forecast Error = [value forecast value actually happenning]
The more sophisticated models of forecast often provide a forecast with smaller error but the cost of development of the model, forecasting and maintaining tend to be high. There has to be a tradeoff between the choice of model and the cost The following figure clearly explains this trade-off:
[John C. Chambers, Satinder K Mullick, and Donald D. Smith, in, “How to choose the right forecasting technique”. Harvard Business Review, Vol. 49 No.4 (July-August1911) as given in charts in the book,-Quantitative Techniques For Business Decisions by Charles A. Gallagher, and Huge J. Watson;] have given description of various forecasting models and rated them from poor to excellent. By proper choice, suited to the purpose, good to excellent results in the forecast can be achieved.