demand forecasting

DEMAND FORECASTING

MEANING

IMPORTANTS

OBJECTIVES

METHODS

What is forecasting all about?

Demand for Mercedes E Class

TimeJan

Feb

Mar Apr May Jun Jul Aug

Actual demand (past sales)

Predicted demand

We try to predict the future by looking back

at the past

Predicted demand looking back six months

WHY DEMAND FORECASTING

• Planning and scheduling production• Acquiring inputs• Making provisions for finances• Formulating pricing strategy• Planning Advertisement

OBJECTIVES

To evolve a suitable production policyTo reduce the cost of purchaseTo determine appropriate price policyTo set sales targets and establish controlTo forecast short-term financial

requirements

Short –term Forecasting

Planning of a new unit or expansion of an existing unit

Planning of long-term financial requirementsPlanning of man-power requirements

OBJECTIVES

Long –term Forecasting

Levels of Forecasting

• Macro level

• Industry level

• Micro level

STEPS IN DEMAND FORECASTING

• Determination of the objectives

• Sub-dividing the task

• Identifying of demand determinants

• Selection of the method

• Collection of Data

• Estimation and interpretation of result

• Reporting

METHODS OF DEMAND FORECASTING

QUALITATIVE TECHNIQUES

Survey Method Direct Interview Method Collective opinion

Delphi Method Controlled Experiments

QUANTITATIVE TECHNIQUES

Barometric Techniques Time Series Analysis Regression Method

SURVEY METHOD

• Surveys are conducted to collect information about the future plans of the potential consumers

• A firm may launch a new product, if the suvey indicates that there is a demand for that particular product in the market.

Direct Interview MethodConsumers are contacted directly to ask them what they intend to buy in futureCollective opinionThe opinions of those who have the feel of the market, like salesman, professional experts, market consultants etc.Advantages•Simple •Quick •Low cost •Reliable DisadvantagesPersonal judgements may go wrongUseful only foe short-term forecasting

DELPHI METHOD

• Applied to uncertain areas where past data or future data are not of much use

• Some expert in an area will be contacted with questionnaires

• A co-ordinator collect all the opinions

• Each expert will be supplied with responses of other experts without revealing their identity

• Expert may revise his opinion, if needed

• Process will be repeated so that all experts come to an agreement

CONTROLLED EXPERIMENTS• Studies and experiments in consumers

behavior are carried out under actual market conditions

• Three or four cities having similarity in population , income level, cultural and social background ,occupational distribution , taste etc.. are chosen

• Various demand determinants like price, advertisement , expenditure etc are changed one by one and these changes on demand are observed

QUANTITATIVE TECHNIQUES

BASED ON DATA AND ANALYTICAL TECHNIQUESBarometric TechniquesTime series AnalysisRegression Method

BAROMETRIC FORECASTING

based on the observed relationships between different economic indicators

It can be divided into three groupsLeading indicatorsCoincident indicatorsLagging indicators

Leading Indicators• which run in advance of changes in demand for a particular product•an increase in the number of building permitsgranted which would lead to an increase in demand for building-related products such as wood, concrete and so onCoincident Indicators•occur alongside changes in demand•an increase in sales would generate an increase in demand for the manufacturers of the goods concernedLagging Indicators•run behind changes in demandNew industrial investment by firms which will only invest in new production facilities when demand is already firmly established.

TIME SERIES ANALYSIS

• Used to predict the future demand for a product based on the past sales and demand.

Simple moving average Weighted moving average Exponential smoothing

Time series: simple moving average

In the simple moving average models the forecast value is

Ft+1 =At + At-1 + … + At-n

n

t is the current period.

Ft+1 is the forecast for next period

n is the forecasting horizon (how far back we look),

A is the actual sales figure from each period.

Example: forecasting sales at Kroger

Kroger sells (among other stuff) bottled spring water

Month Bottles

Jan 1,325

Feb 1,353

Mar 1,305

Apr 1,275

May 1,210

Jun 1,195

Jul ?

What will the sales

be for July?

What if we use a 3-month simple moving average?

FJul =AJun + AMay + AApr

3= 1,227

What if we use a 5-month simple moving average?

FJul =AJun + AMay + AApr + AMar + AFeb

5= 1,268

Time series: weighted moving average

We may want to give more importance to some of the data…

Ft+1 = wt At + wt-1 At-1 + … + wt-n At-n

wt + wt-1 + … + wt-n = 1

t is the current period.

Ft+1 is the forecast for next period

n is the forecasting horizon (how far back we look),

A is the actual sales figure from each period.

w is the importance (weight) we give to each period

Time Series: Exponential Smoothing (ES)

Main idea: The prediction of the future depends mostly on the most recent observation, and on the error for the latest

forecast.

Smoothing

constant alpha α

Denotes the importance of the past

error

Exponential smoothing: the method

Assume that we are currently in period t. We calculated the forecast for the last period (Ft-1) and we know the actual demand last period (At-1) …

)( 111 tttt FAFF

The smoothing constant α expresses how much our forecast will react to observed differences…

If α is low: there is little reaction to differences.

If α is high: there is a lot of reaction to differences.

Linear regression in forecasting

Linear regression is based on

1. Fitting a straight line to data

2. Explaining the change in one variable through changes in other variables.

By using linear regression, we are trying to explore which independent variables affect the dependent variable

dependent variable = a + b (independent variable)

YY XXii ii aa bb

• Shows linear relationship between dependent & explanatory variables– Example: Diapers & # Babies (not time)

Dependent Dependent (response) variable(response) variable

Independent (explanatory) Independent (explanatory) variablevariable

SlopeSlopeY-interceptY-intercept

^̂

Linear Regression Model

Example: do people drink more when it’s cold?

Alcohol Sales

Average Monthly

Temperature

Which line best fits the data?

The best line is the one that minimizes the error

bXaY

The predicted line is …

So, the error is …

iiε Y-yi

Where: ε is the error y is the observed value Y is the predicted value

Conclusion

• Accurate demand forecasting requires– Product knowledge

– Knowledge about the customer

– Knowledge about the environment