Você está na página 1de 4

FORECASTING

Forecasting Definition: Forecasting refers to the prediction of future based on past and present data. It
may not reduce the complications and uncertainty of the future but it can help the management to
tackle uncertainty

Characteristics of a forecast:

 Forecasting in concerned with future events.


 It shows the probability of happening of future events.
 It analysis past and present data.
 It uses statistical tools and techniques.
 It uses personal observations.

Types of forecast:
Forecast can be classified in two categories

(On the basis of nature of state):


1. Passive forecast: where prediction about future is based on the assumption that firm does not
change the course of its action
2. Active forecast: where forecasting is done under the condition of likely future changes in the
actions by firm

(On the basis of time period):


1. Short run forecast: when forecasting is done for short time horizon
2. Long run forecast: when forecasting is done for long term horizon

Steps of forecasting:
Following are the steps in forecasting
• Identification of objectives
• Determining the nature of goods under consideration
• Selecting a proper method of forecasting
• Collecting and analyzing data
• Interpretation of results

Limitations of forecasting
 The collection and analysis of data about the past, present and future involves a lot of time and
money
 Forecasting can only estimate the future events. It cannot guarantee that these events will take
place in the future
 Forecasting is based on certain assumptions
 Forecasting requires proper judgment and skills on the part of managers.
Forecasting technique: Method or procedure that is used in forecasting is known as forecasting
technique.

Elements of forecasting techniques:

1. Time horizon: length of time for which decision is being made has a bearing on the appropriate
technique. Qualitative techniques are better in long period and quantitative techniques are
better in short run.

2. Levels of forecast:
a. Macroeconomic forecasting-it is concerned with business condition over the whole economy.
b. Industry (market) demand forecasting: provides information regarding direction in which the
whole industry will be moving
c. Firm (company) level forecasting: concerned with forecasting about company’s own products
independent of other firm
d. product-line forecasting: helps the firm to decide which of the products to be focused more

3. Stability: forecasting situation that relatively stable over time requires less attention.

4. Pattern of Data: Greater the latest data more accurate will be forecasting

5. Cost: Several cost elements are involved with forecasting procedures


6. Accuracy: accuracy is measured by degree of deviation between past and current actual
performance

Types of Forecasting Methods/ techniques:

Quantitative forecasting methods


These methods can be used when:
• Past information about variable being forecast is available
• Information can be quantified
• Assumption is that pattern of past will continue into the future
Quantitative method classification
Quantitative methods can be classified into two categories

Time series method: a set of data over regular interval of time is called as time series. Time series
methods are used to identify patterns of change in historical data over regular intervals of time.
Pattern of change are identified to arrive at an estimate for the future.

Causal forecasting methods: these methods are based on the assumptions that the variable which
we intend to forecast has a cause-effect relationship with one or more other variables.

Time series methods


Time series methods are concerned with taking some observed historical pattern for some variable and
projecting this pattern into the future using a mathematical formula. These methods don’t attempt to
suggest why the variable under study will take some future value.

Some of the time series methods are :


Freehand method
Smoothing methods
 Moving average
 Weighted moving average
 Exponential smoothing methods

Freehand method:
In this method all of the data is plotted on a graph. A forecast can be obtained simply by extending the
trend line.

Conditions to be met in this method are:


 Trend line should be smooth- a straight line or mix of long gradual curves
 Sum of squares of vertical deviations of the observations from trend line should be as small as
possible

Limitations of freehand method


 This method is highly subjective in nature
 It is very time consuming to construct a freehand trend

Smoothing methods
Objective of smoothing methods is to smoothen out the random variations due to irregular components
of the time series and thereby provide us with an overall impression of the pattern of movement in data
over time

Some of the smoothing methods are


 Moving average
 Weighted moving average
 Exponential smoothing
Moving average method
 In this method data beyond certain time period is considered as irrelevant. e.g. In moving
average of 10 years, past data of more than 10 years is considered as irrelevant.
 This method is subjective in nature and depends on the length of time period chosen for
calculating average.
 As the size of time period increases, it smoothens out the variations better.

Weighted moving average


In moving averages, each observation is given equal importance. While in weighted moving average
different weights are assigned to different time.

Exponential smoothing method


 Exponential smoothing is a type of moving average forecasting technique which weighs past
data in an exponential manner.
 Advantage of this method is that we need to have only two values i.e. last period forecast and
last period actual demand.

Qualitative Forecasting techniques


Expert Opinion
 In this method of demand forecasting, the firm makes an effort to obtain the opinion of experts
who have long standing experience in the field of enquiry related to the product under
consideration. If the forecast is based on the opinion of several experts then the approach is
called forecasting through the use of panel consensus.
 Although the panel consensus method usually results in forecasts that embody the collective
wisdom of consulted experts, it may be at times unfavorably affected by the force of personality
of one or few key individuals.

Delphi Technique
 To counter the disadvantage of panel consensus, another approach is developed called the
Delphi method.
 In this method a panel of experts (consisting of usually 5-20 members) is individually presented
a series of questions pertaining to the forecasting problem. Responses acquired from the
experts are analyzed by an independent party that will provide the feedback to the panel
members through letters/mail.
 Based on the responses of other individuals, each expert is then asked to make a revised
forecast. This process continues till a consensus is reached or until further iterations generate no
change in estimates
Advantage
 Helps individual panel members in assessing their forecasts
 Anonymity

Disadvantage
 Time consuming
 Costly
 Most knowledgeable experts in the industry will command more fees
 Experts may be reluctant to be influenced by the opinions of others

Você também pode gostar