Sales Forecasting
Content
INTRODUCTION:
An experimental procedure that provides an opportunity to test a new product
or a new marketing plan under realistic market conditions.
Test marketing is an experiment conducted in a field laboratory (the test
market) comprising of actual stores and real-life buying situations, where
the buyers is unaware of participation.
Test marketing may last from few weeks to several months.
Market testing depends on different factors:
The investment cost and risk , time pressure and the research cost .
High investment-high risk products where the chance of failure is high.
High risk products those who creates new product categories or have novel
features.
The amount of market testing is reduced if the company is having great time
pressure because the season is just starting.
CONSUMER GOODS MARKET TESTING:
•
Sales wave research
•
Simulated test marketing
•
Controlled test marketing
•
Test markets
1. Sales wave research:
In sales wave research a consumer who initially tried the product at no cost are
reoffered it, or a competitor’s product at slightly reduced prices. The offer may be made
as many as five times (sales waves), while the company notes how many consumers
selected the product again and their reported level of satisfaction.
It’s quick, secure, and can be carried out without final packaging.
2. Simulated test marketing:
30 to 40 qualified shoppers were called and questioned brand familiarity and
preferences in a specific product category.
These consumers attended a brief screening of well known as well as new TV
commercials or print ads.
Consumer are provided small amount of money and they are invited to a store
where they may buy any items.
This provides a measure of the ads relative effectiveness against competing ads
in the market.
This method gives fairly accurate result of effect of ads and trial rates. The
results are incorporated in to new product forecasting model to project ultimate sales
levels.
3. Controlled test marketing:
A panel of stores carries new product for a fee.
Specific number of stores and geographic location.
Controlled shelf position; number of facings,
Sales are measured at check out.
A sample of consumers interviewed later to give their
impression of the product.
Disadvantage:
This technique exposes the product and its
features to competitors’ scrutiny.
4. Test markets:
Few representative cities,
Good shelf exposure.
Full Advertisement and Promotion campaign.
In this method company have to take following decisions:
-
HOW MANY TEST CITIES?
-
WHICH CITIES?
-
LENGTH OF TEST?
-
WHAT INFORMATION TO BE COLLECTED?
-
WHAT ACTION TO TAKE?
Business goods market testing:
Expensive industrial goods and new technologies will normally undergo two type of
test marketing.:
Alpha testing (within the company)
Beta testing (with outside customers)
During beta testing the company’s technical people observes how test customers use
the product.
The company can also observe how much value the equipment to the customers
operation as a cue to subsequent pricing.
The company asks test customers their purchase intention and other reaction after the
test.
Disadvantages:
Customer who comes in might not represent the target market.
Customer might place early orders that can’t be filled.
Sales Forecasting
•
It is an estimate of sales during a specified future period which is tied to a proposed
marketing plan and which assumes a particular set of uncontrollable and competitive
forces.
•
Starting point of short term (3 to 6 months), medium term (6 to 24 months), and long
term planning.
•
Short/medium term forecasting-basis for determining a company’s production
schedule.
•
Long term forecasting - useful in determining what new facilities, labor, and
funding will be needed.
•
Sales forecasting is not just the estimation of sales; it is also matching sales
opportunities-actual and potential- with sales planning and procedures
Forecasting Process
•
The forecasting process is defined as the series of decisions and actions taken by
a business organization in:
Identifying the forecasting objectives
Determining the independent and dependent variables
Developing a forecasting procedure
Using the available data in the selected method to estimate the sales in
future
Sales Forecasting Process
Determine independent and dependent variables
Develop forecasting procedure
Forecasting process
finalize the fo
Sales Forecasting Methods
•
The sales forecasting method is a procedure for estimating how much of a given product
(or product line) can be sold if a given marketing program is implemented. No sales
forecasting method is foolproof-each is subjected to some error.
•
Well managed companies do not rely upon a single sales forecasting method but use
several methods.
•
Roughly same forecast results-more confidence placed in the results
•
Greatly different forecasts-further study
Sales forecasting is divided into two methods
Qualitative methods
Jury of Executive Opinion
Sales force opinion method
Survey of buyer intentions
Jury of executive opinion
This can be done in two ways:
1.
By one seasoned individual (usually in a small company).
2.
By a group of individuals, their responses are pooled into one forecast
•
Best used when executives have a strong working knowledge of the area and other
sources of data is hard to find.
Advantages
•
•
Can be done easily and quickly without a lot of elaborate statistical manipulations
Incorporated a variety of opinions from executives
Disadvantages
•
•
•
•
Over reliance on personal opinion that is not backed up with facts
People with little marketing and sales knowledge may be involved in making the
decisions
Lack of statistics
May be undue influence in certain case.
Jury of executive opinion
– Variations
o Delphi Technique- Members of the jury never meet and make anonymous
forecasts. The leader averages and returns a median or mean forecast to each
member of the jury. Each member evaluates and revises the forecast until a
consensus is met.
o The Nominal Group Technique is a face to face Delphi method, allowing
group discussion
o Factor Listing- when each member of the jury is required to list factors that
will have a positive or negative impact. A consensus is then sought on the
magnitude of each factor so a prediction can be made.
o
The Dialectical Inquiry method poses sub-groups to challenge the group’s
findings with alternative scenarios.
Sales force composite
Also known as “the grass-roots approach”.
Individual salespersons forecast sales for their territories
Individual forecasts are combined and modified by the sales manager to form the
company sales forecast.
Best used when a highly trained and specialized sales force is used.
Advantages
Attention is called to the actual sales potential for each territory.
It uses the knowledge of those closest to the market.
Salesperson is more likely to believe their forecast is correct.
It places more responsibility on the salesperson.
Disadvantages
Salespeople are not trained in forecasting.
May try to underestimate due to quotes.
Salespeople may not spend the time needed.
Survey of buyer intentions
Also called user’s expectations method
It is a qualitative forecasting method that samples opinions among groups of present
and potential customers concerning their purchase intentions.
The survey method is based on the opinion of buyers and consumers.
More useful in industrial products than in consumer goods.
Advantages
•
•
Useful in predicting short-term and intermediate sales for firms that serve only a few
customers
People that are going to purchase the product are involved
Disadvantages
•
Intentions to buy may not result in actual purchases (They may report what they want
to buy, but not what they are capable of buying)
•
•
•
•
Customers may not want to disclose that information
Effects of derived demand may make forecasting difficult
Time-consuming
Expensive
Quantitative methods
Market Test
Trend Projections
Exponential smoothening method
Moving Averages
Regression Analysis
Market Test
•
A quantitative forecasting method that introduces a new product, price, promotional
campaign, or other marketing variable in a relatively small test market location in
order to assess consumer reaction.
•
Provides realistic information on actual purchases rather than on intent to buy
•
Alerts competition to new-product plans
•
Time-consuming
•
Expensive
Trend Projection
•
A quantitative sales forecasting method that estimates future sales through statistical
analyses of historical sales patterns.
•
The least squares method is formalization of the eyeball-fitting or graphical technique.
It is used to mathematically project the trend line to the forecasting period with the
time as the independent variable that influences the dependent variable i.e sales.
Advantages
Quick
Inexpensive
Effective with stable customer demand and environment
Disadvantages
O b s er v d S a le s F o r e c a s t S a le s
60
50
S
a
l
e
s
4 0 T r en d
L in e
30
20
10
0
19 84 19 8 5 19 8 6 19 87 19 8 19 8 19 0
T im e
Assume the future will continue the past
Ignores environmental changes
Moving Averages Method
•
Moving averages are used to allow for marketplace factors changing at different rates and at
different times.
Month
Actual
1
60
2
65
3 month moving average
Forecast
3
68
(60+65+68/3)=
64
4
73
69
64
5
69
70
69
6
65
69
70
7
62
65
69
8
59
62
65
9
63
61
62
10
66
63
61
11
58
62
63
12
60
61
62
L i n e a r R e la t i o n s h i p C u r v i l n e a r R e l a t i o n s h i p
s
a
S
l e
a
S
l e
s
Regression Analysis
0
P o p u l a ti o n
(A )
0
P o p u l a ti o n
(B )
•
Regression analysis is a statistical method used to incorporate independent factors that are
thought to influence sales into the forecasting procedure.
•
Reveals average relationship between two variables and this makes possible estimation or
prediction.
Naive Method
•
The following formula shows how to adjust the naïve method to account for a change in rate of
sales levels. The formula is stated this way:
Next Year’s Sales = This Year’s Sales X This Year’s Sales
Last Year’s Sales
Exponential Smoothing
•
•
•
•
It is similar to the moving- average forecasting method
The forecaster is allowed to vary the weights assigned to past data points
The method is used to forecast only one period in the future
Exponential smoothing techniques vary in terms of how they address trend, seasonality, cyclical
and irregular influences.
•
It is basically a weighted moving average of all past data
•
It allows consideration of all past data, but less weight is placed on data.
Next Year’s Sales = a (This Year’s Sales) + (1 – a) (This Year’s Forecast)
Advantages
Quick
Inexpensive
Effective with stable customer demand
Emphasizes more recent data
Disadvantages
Severe due to emphasis on recent data
Assume the future will continue the past
Ignores environmental changes
FORCASTING
METHOD
TIME SPAN
MATHEMATICAL COMPUTER ACCURACY
SOPHISTICATION NEED
Executive
Opinion
Short to
medium
Minimal
Not essential
Limited
Delphi Method
Medium to
long
Minimal
Not essential
Limited; good in
dynamic conditions
Sales Force
Composite
Short to
medium
Minimal
Not essential
Accurate under
dynamic conditions
User’s
Expectations
Short to
medium
Minimal
Not essential
Limited
Test Markets
Medium
Needed
Needed
Accurate
Naïve Method
Present to
medium
Minimal
Not essential
Limited
Moving Average Short to long
Minimal
Helpful
Accurate under stable
conditions
Exponential
Smoothing
Short to
medium
Minimal
Helpful
Accurate under stable
conditions
Least Squares
Short to long
Needed
Desirable
Varies widely
Regression
Analysis
Short to
Medium
Needed
Essential
Accurate if variable
relationships stable
Time Series Analysis
One of the most frequently used forecasting methods is time series analysis.
• Time series refers to the values of a variable arranged chronologically by days, weeks, months,
quarters, or years.
• Time-series analysis attempts to forecast future values of the time series by examining past
observations.
• The assumption is that the time series will continue to move as in the past.
The classical time series model takes the following form:
Y=T*S*C*I
This approach to economic forecasting assumes that economic time series can be decomposed into four
elements (T, S, C, I)
Decomposition of a Time Series
Trend - T: A trend is relatively smooth long-term movements of a time series.
Seasonal variation - S: Fairly regular patterns that repeat each year. because of seasonal factors.
Cyclical variation – C: Medium term variation due to the effects of the business cycle.
Irregular variation - I: Due to unexpected or irregular occurrences, No trends or patterns
An experimental procedure that provides an opportunity to test a new product
or a new marketing plan under realistic market conditions.
Test marketing is an experiment conducted in a field laboratory (the test
market) comprising of actual stores and real-life buying situations, where
the buyers is unaware of participation.
Test marketing may last from few weeks to several months.
Market testing depends on different factors:
The investment cost and risk , time pressure and the research cost .
High investment-high risk products where the chance of failure is high.
High risk products those who creates new product categories or have novel
features.
The amount of market testing is reduced if the company is having great time
pressure because the season is just starting.
CONSUMER GOODS MARKET TESTING:
•
Sales wave research
•
Simulated test marketing
•
Controlled test marketing
•
Test markets
1. Sales wave research:
In sales wave research a consumer who initially tried the product at no cost are
reoffered it, or a competitor’s product at slightly reduced prices. The offer may be made
as many as five times (sales waves), while the company notes how many consumers
selected the product again and their reported level of satisfaction.
It’s quick, secure, and can be carried out without final packaging.
2. Simulated test marketing:
30 to 40 qualified shoppers were called and questioned brand familiarity and
preferences in a specific product category.
These consumers attended a brief screening of well known as well as new TV
commercials or print ads.
Consumer are provided small amount of money and they are invited to a store
where they may buy any items.
This provides a measure of the ads relative effectiveness against competing ads
in the market.
This method gives fairly accurate result of effect of ads and trial rates. The
results are incorporated in to new product forecasting model to project ultimate sales
levels.
3. Controlled test marketing:
A panel of stores carries new product for a fee.
Specific number of stores and geographic location.
Controlled shelf position; number of facings,
Sales are measured at check out.
A sample of consumers interviewed later to give their
impression of the product.
Disadvantage:
This technique exposes the product and its
features to competitors’ scrutiny.
4. Test markets:
Few representative cities,
Good shelf exposure.
Full Advertisement and Promotion campaign.
In this method company have to take following decisions:
-
HOW MANY TEST CITIES?
-
WHICH CITIES?
-
LENGTH OF TEST?
-
WHAT INFORMATION TO BE COLLECTED?
-
WHAT ACTION TO TAKE?
Business goods market testing:
Expensive industrial goods and new technologies will normally undergo two type of
test marketing.:
Alpha testing (within the company)
Beta testing (with outside customers)
During beta testing the company’s technical people observes how test customers use
the product.
The company can also observe how much value the equipment to the customers
operation as a cue to subsequent pricing.
The company asks test customers their purchase intention and other reaction after the
test.
Disadvantages:
Customer who comes in might not represent the target market.
Customer might place early orders that can’t be filled.
Sales Forecasting
•
It is an estimate of sales during a specified future period which is tied to a proposed
marketing plan and which assumes a particular set of uncontrollable and competitive
forces.
•
Starting point of short term (3 to 6 months), medium term (6 to 24 months), and long
term planning.
•
Short/medium term forecasting-basis for determining a company’s production
schedule.
•
Long term forecasting - useful in determining what new facilities, labor, and
funding will be needed.
•
Sales forecasting is not just the estimation of sales; it is also matching sales
opportunities-actual and potential- with sales planning and procedures
Forecasting Process
•
The forecasting process is defined as the series of decisions and actions taken by
a business organization in:
Identifying the forecasting objectives
Determining the independent and dependent variables
Developing a forecasting procedure
Using the available data in the selected method to estimate the sales in
future
Sales Forecasting Process
Determine independent and dependent variables
Develop forecasting procedure
Forecasting process
finalize the fo
Sales Forecasting Methods
•
The sales forecasting method is a procedure for estimating how much of a given product
(or product line) can be sold if a given marketing program is implemented. No sales
forecasting method is foolproof-each is subjected to some error.
•
Well managed companies do not rely upon a single sales forecasting method but use
several methods.
•
Roughly same forecast results-more confidence placed in the results
•
Greatly different forecasts-further study
Sales forecasting is divided into two methods
Qualitative methods
Jury of Executive Opinion
Sales force opinion method
Survey of buyer intentions
Jury of executive opinion
This can be done in two ways:
1.
By one seasoned individual (usually in a small company).
2.
By a group of individuals, their responses are pooled into one forecast
•
Best used when executives have a strong working knowledge of the area and other
sources of data is hard to find.
Advantages
•
•
Can be done easily and quickly without a lot of elaborate statistical manipulations
Incorporated a variety of opinions from executives
Disadvantages
•
•
•
•
Over reliance on personal opinion that is not backed up with facts
People with little marketing and sales knowledge may be involved in making the
decisions
Lack of statistics
May be undue influence in certain case.
Jury of executive opinion
– Variations
o Delphi Technique- Members of the jury never meet and make anonymous
forecasts. The leader averages and returns a median or mean forecast to each
member of the jury. Each member evaluates and revises the forecast until a
consensus is met.
o The Nominal Group Technique is a face to face Delphi method, allowing
group discussion
o Factor Listing- when each member of the jury is required to list factors that
will have a positive or negative impact. A consensus is then sought on the
magnitude of each factor so a prediction can be made.
o
The Dialectical Inquiry method poses sub-groups to challenge the group’s
findings with alternative scenarios.
Sales force composite
Also known as “the grass-roots approach”.
Individual salespersons forecast sales for their territories
Individual forecasts are combined and modified by the sales manager to form the
company sales forecast.
Best used when a highly trained and specialized sales force is used.
Advantages
Attention is called to the actual sales potential for each territory.
It uses the knowledge of those closest to the market.
Salesperson is more likely to believe their forecast is correct.
It places more responsibility on the salesperson.
Disadvantages
Salespeople are not trained in forecasting.
May try to underestimate due to quotes.
Salespeople may not spend the time needed.
Survey of buyer intentions
Also called user’s expectations method
It is a qualitative forecasting method that samples opinions among groups of present
and potential customers concerning their purchase intentions.
The survey method is based on the opinion of buyers and consumers.
More useful in industrial products than in consumer goods.
Advantages
•
•
Useful in predicting short-term and intermediate sales for firms that serve only a few
customers
People that are going to purchase the product are involved
Disadvantages
•
Intentions to buy may not result in actual purchases (They may report what they want
to buy, but not what they are capable of buying)
•
•
•
•
Customers may not want to disclose that information
Effects of derived demand may make forecasting difficult
Time-consuming
Expensive
Quantitative methods
Market Test
Trend Projections
Exponential smoothening method
Moving Averages
Regression Analysis
Market Test
•
A quantitative forecasting method that introduces a new product, price, promotional
campaign, or other marketing variable in a relatively small test market location in
order to assess consumer reaction.
•
Provides realistic information on actual purchases rather than on intent to buy
•
Alerts competition to new-product plans
•
Time-consuming
•
Expensive
Trend Projection
•
A quantitative sales forecasting method that estimates future sales through statistical
analyses of historical sales patterns.
•
The least squares method is formalization of the eyeball-fitting or graphical technique.
It is used to mathematically project the trend line to the forecasting period with the
time as the independent variable that influences the dependent variable i.e sales.
Advantages
Quick
Inexpensive
Effective with stable customer demand and environment
Disadvantages
O b s er v d S a le s F o r e c a s t S a le s
60
50
S
a
l
e
s
4 0 T r en d
L in e
30
20
10
0
19 84 19 8 5 19 8 6 19 87 19 8 19 8 19 0
T im e
Assume the future will continue the past
Ignores environmental changes
Moving Averages Method
•
Moving averages are used to allow for marketplace factors changing at different rates and at
different times.
Month
Actual
1
60
2
65
3 month moving average
Forecast
3
68
(60+65+68/3)=
64
4
73
69
64
5
69
70
69
6
65
69
70
7
62
65
69
8
59
62
65
9
63
61
62
10
66
63
61
11
58
62
63
12
60
61
62
L i n e a r R e la t i o n s h i p C u r v i l n e a r R e l a t i o n s h i p
s
a
S
l e
a
S
l e
s
Regression Analysis
0
P o p u l a ti o n
(A )
0
P o p u l a ti o n
(B )
•
Regression analysis is a statistical method used to incorporate independent factors that are
thought to influence sales into the forecasting procedure.
•
Reveals average relationship between two variables and this makes possible estimation or
prediction.
Naive Method
•
The following formula shows how to adjust the naïve method to account for a change in rate of
sales levels. The formula is stated this way:
Next Year’s Sales = This Year’s Sales X This Year’s Sales
Last Year’s Sales
Exponential Smoothing
•
•
•
•
It is similar to the moving- average forecasting method
The forecaster is allowed to vary the weights assigned to past data points
The method is used to forecast only one period in the future
Exponential smoothing techniques vary in terms of how they address trend, seasonality, cyclical
and irregular influences.
•
It is basically a weighted moving average of all past data
•
It allows consideration of all past data, but less weight is placed on data.
Next Year’s Sales = a (This Year’s Sales) + (1 – a) (This Year’s Forecast)
Advantages
Quick
Inexpensive
Effective with stable customer demand
Emphasizes more recent data
Disadvantages
Severe due to emphasis on recent data
Assume the future will continue the past
Ignores environmental changes
FORCASTING
METHOD
TIME SPAN
MATHEMATICAL COMPUTER ACCURACY
SOPHISTICATION NEED
Executive
Opinion
Short to
medium
Minimal
Not essential
Limited
Delphi Method
Medium to
long
Minimal
Not essential
Limited; good in
dynamic conditions
Sales Force
Composite
Short to
medium
Minimal
Not essential
Accurate under
dynamic conditions
User’s
Expectations
Short to
medium
Minimal
Not essential
Limited
Test Markets
Medium
Needed
Needed
Accurate
Naïve Method
Present to
medium
Minimal
Not essential
Limited
Moving Average Short to long
Minimal
Helpful
Accurate under stable
conditions
Exponential
Smoothing
Short to
medium
Minimal
Helpful
Accurate under stable
conditions
Least Squares
Short to long
Needed
Desirable
Varies widely
Regression
Analysis
Short to
Medium
Needed
Essential
Accurate if variable
relationships stable
Time Series Analysis
One of the most frequently used forecasting methods is time series analysis.
• Time series refers to the values of a variable arranged chronologically by days, weeks, months,
quarters, or years.
• Time-series analysis attempts to forecast future values of the time series by examining past
observations.
• The assumption is that the time series will continue to move as in the past.
The classical time series model takes the following form:
Y=T*S*C*I
This approach to economic forecasting assumes that economic time series can be decomposed into four
elements (T, S, C, I)
Decomposition of a Time Series
Trend - T: A trend is relatively smooth long-term movements of a time series.
Seasonal variation - S: Fairly regular patterns that repeat each year. because of seasonal factors.
Cyclical variation – C: Medium term variation due to the effects of the business cycle.
Irregular variation - I: Due to unexpected or irregular occurrences, No trends or patterns
