Forecasting 8th Ed.

4
Forecasting
SCM 352
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Outline
•
•
•
•
Global Company Profile: Disney World
What is Forecasting?
Types of Forecasts
Forecasting Approaches
– Overview of Qualitative & Quantitative Methods
• Time-Series Forecasting
• Monitoring and Controlling Forecasts
Famous Forecasting Quotes
"Those who have knowledge, don't predict.
Those who predict, don't have knowledge. "
-- Lao Tzu, 6th Century BC Chinese Poet
"It is often said there are two types of forecasts
... lucky or wrong!!!! "
-- "Control" magazine (Inst. of Ops. Mgmt.)
(http://www.met.rdg.ac.uk/cag/forecasting/quotes.html)
Forecasting at Disney World
•
•
•
•
•
•
Global portfolio includes parks in Hong Kong, Paris,
Tokyo, Orlando, and Anaheim
Revenues are derived from people – how many visitors
and how they spend their money
Daily management report contains only the forecast
and actual attendance at each park
Disney generates daily, weekly, monthly, annual, and 5year forecasts
Forecast used by labor management, maintenance,
operations, finance, and park scheduling
Forecast used to adjust opening times,
rides, shows, staffing levels, and
guests admitted
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Forecasting at Disney World
•
•
•
•
•
•
20% of customers come from outside the USA
Economic model includes gross domestic product,
cross-exchange rates, arrivals into the USA
A staff of 35 analysts and 70 field people survey 1
million park guests, employees, and travel
professionals each year
Inputs to the forecasting model include airline specials,
Federal Reserve policies, Wall Street trends,
vacation/holiday schedules for 3,000 school districts
around the world
Average forecast error for the 5-year forecast is 5%
Average forecast error for annual forecasts is between
0% and 3%
© 2011 Pearson Education, Inc. publishing as Prentice Hall
What is Forecasting?
•
Process of predicting
a future event
•
Underlying basis of
all business decisions
–
–
–
–
Production
Inventory
Personnel
Facilities
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Sales will
be $200
Million!
Forecasting Time Horizons
• Short-range forecast
• Up to 1 year, generally less than 3 months
• Purchasing, job scheduling, workforce levels, job
assignments, production levels
• Medium-range forecast
• 3 months to 3 years
• Sales and production planning, budgeting
• Long-range forecast
• 3+ years
• New product planning, facility location, research
and development
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Types of Forecasts
• Economic forecasts
– Address business cycle, e.g., inflation rate, money
supply, housing starts, etc.
• Technological forecasts
– Predict rate of technological progress
– Impacts development of new products
• Demand forecasts
– Predict sales of existing products and services
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Strategic Importance of Forecasting
• Human Resources – Hiring, training, laying off
•
•
workers
Capacity – Capacity shortages can result in
undependable delivery, loss of customers, loss
of market share
Supply Chain Management
– Good supplier relations
and price advantages
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Forecasting Approaches
Qualitative Methods
Quantitative Methods
Used when situation
is vague & little data
exist
Used when situation is
stable & historical data
exist
New products
New technology
Existing products
Current technology
Involves intuition,
experience
e.g., forecasting
sales on Internet
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Involves mathematical
techniques
e.g., forecasting sales
of color televisions
Overview of Qualitative Methods
• Jury of executive opinion
– Pool opinions of high-level executives, sometimes
augment by statistical models
– ‘Group-think’ disadvantage
• Sales force composite
– Estimates from individual salespersons are
reviewed for reasonableness, then aggregated
– Sales reps know customers’ wants
• Delphi method
– Panel of experts, queried iteratively
• Consumer market survey
– Ask the customer
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Quantitative Approaches
1. Naive approach
2. Moving averages
3. Exponential smoothing
Time-Series
Models
4. Trend projection
5. Linear regression
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Associative
Model
Time Series Forecasting
• Set of evenly spaced numerical data
• Obtained by observing response variable at
regular time periods
• Forecast based only on past values, no other
variables important
• Assumes that factors influencing past and present
will continue influence in future
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Time Series Forecasting
Trend
Cyclical
Seasonal
Random
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Components of Demand
Demand for product or service
Trend
component
Seasonal peaks
Actual demand
line
Average demand
over 4 years
Random variation
|
1
|
2
|
3
Time (years)
© 2011 Pearson Education, Inc. publishing as Prentice Hall
|
4
Naive Approach
• Assumes demand in next period is the same as
demand in most recent period
– If May sales were 48, then June sales will be 48
• Sometimes can be cost effective and efficient
• Can be good starting point
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Moving Average Method
• MA is a series of arithmetic means
• Used if little or no trend
• Used often for smoothing
– Provides overall impression of data over time
• Equation
∑ demand in previous n periods
Moving average =
n
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Potential Problems With MA
• Increasing n smooths the forecast but makes it
•
•
less sensitive to changes
Do not forecast trends well
Require extensive historical data
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Moving Average Example
Month
Actual
Shed Sales
January
February
March
April
May
June
July
10
12
14
16
18
23
26
© 2011 Pearson Education, Inc. publishing as Prentice Hall
3-Month
Moving Average
(10 + 12 + 14)/3 = 12
(12 + 14 + 16)/3 = 14
(14 + 16 + 18)/3 = 16
(16 + 18 + 23)/3 = 19
Weighted Moving Average Method
• Used when trend is present
– Older data usually less important
• Weights based on intuition
– Ranges between 0 & 1, & sum to 1.0
• Equation
Σ(Weight for period n) (Demand in period n)
WMA =
ΣWeights
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Weighted Moving Average Example
Month
Actual
Shed Sales
January
February
March
April
May
June
July
10
12
14
16
18
23
26
3-Month
Moving Average
(10*0.2 + 12*0.3 + 14*0.5) = 12.6
(12*0.2 + 14*0.3 + 16*0.5) = 14.6
(14*0.2 + 16*0.3 + 18*0.5) = 16.6
(16*0.2 + 18*0.3 + 23*0.5) = 20.1
Weights: heaviest weights applied to most recent month – 0.5, 0.3, 0.2
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Exponential Smoothing Method
• Form of weighted moving average
– Weights decline exponentially
– Most recent data weighted most
• Requires smoothing constant (α)
– Ranges from 0 to 1
– Select the value of α that gives us the lowest
forecast error (MAD or MSE)
• Involves little record keeping of past data
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Exponential Smoothing Equations
• Ft = Ft-1 + α(At-1 - Ft-1)
– Use for computing forecast
• Ft = αAt-1 + α(1-α)At-2 + α(1- α)2·At-3
+ α(1- α)3At-4 + ... + α(1- α)t-1·A0
– Ft = Forecast value
– At = Actual value
– α = Smoothing constant
• What happens when α = 1?
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Problem 4.6, Page 140
(b) What is the forecast for January?
[iv] Exponential smoothing, α = 0.3
FSep = 18
FOct = 18 + 0.3(20-18) = 18.6
FNov = 18.6 + 0.3(20-18.6) = 19.02
FDec = 19.02 + 0.3(21-19.02) = 19.6
FJan = 19.6 + 0.3(23-19.6) = 20.62
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Month
Sales
January
20
February
21
March
15
April
14
May
13
June
16
July
17
August
18
September
20
October
20
November
21
December
23
Trend Projections
Fitting a trend line to historical data points
to project into the medium-to-long-range
Linear trends can be found using the least
squares technique
y^ = a + bx
^
where y
= computed value of the variable to
be predicted (dependent variable)
a = y-axis intercept
b = slope of the regression line
x = the independent variable
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Least Squares Method
Equations to calculate the regression variables
y^ = a + bx
Σxy - nxy
b=
Σx2 - nx2
a = y - bx
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Interpretation of Coefficients
^ & advertising (x)
• Example: Sales (y)
• Slope (b)
^ changes by b for each 1 unit
– Estimated y
increase in x
^ is expected to increase
• If b = 2, then sales (y)
by 2 for each 1 unit increase in advertising (x)
• Y-intercept (a)
– Average value of y^ when x = 0
^ is expected to
• If a = 4, then average sales (y)
be 4 when advertising (x) is 0
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Selecting a Forecasting Model
• You want to achieve:
– No pattern or direction in forecast error
• Error = (At - Ft) = (Actual - Forecast)
• Seen in plots of errors over time
– Smallest forecast error
• Mean square error (MSE)
• Mean absolute deviation (MAD)
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Measuring Forecast Error
Mean Absolute Deviation (MAD)
∑ |actual - forecast|
MAD =
n
Mean Squared Error (MSE)
MSE =
∑ (forecast error)2
n
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Comparison of Forecast Error
Quarter
Actual
Tonnage
Unloaded
Rounded
Forecast
using
Model A
1
2
3
4
180
168
159
175
179
167
160
184
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Absolute
Deviation
for
Model A
Rounded
Forecast
using
Model B
177
171
156
172
Absolute
Deviation
for
Model B
Forecast Error - MAD
MAD =
Quarter
Rounded
∑
|deviation|
Actual
Forecast
Tonnage n
with
Unloaded
Model A
For1Model A
180
2
3
4
179
168
167
=159
(1+1+1+9)/4
160
=175
12/4 = 3 184
For Model B
Absolute
Deviation
for
Model A
Rounded
Forecast
with
Model B
Absolute
Deviation
for
Model B
1
1
1
9
12
177
171
156
172
3
3
3
3
12
= (3+3+3+3)/4
= 12/4 = 3
Model A and Model B have the same MAD values.
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Forecast Error - MSE
2
Rounded
∑ (forecast
error)
Actual
Forecast
MSE =
Tonnage n
with
Quarter
Unloaded
Model A
For 1Model A180
2
3
4
179
168
167
(1+1+1+81)/4
159
160
175= 21
184
84/4
=
=
For Model B
Absolute
Deviation
for
Model A
Rounded
Forecast
with
Model B
Absolute
Deviation
for
Model B
1
1
1
9
12
177
171
156
172
3
3
3
3
12
= (9+9+9+9)/4
= 36/4 = 9
Model B has a smaller MSE (=9) than Model A (=21)
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Monitoring & Controlling Forecasts
•
•
•
Tracking signal
Measures how well the forecast is
predicting actual values
Ratio of running sum of forecast errors
(RSFE) to mean absolute deviation (MAD)
• Good tracking signal has low values
• If forecasts are continually high or low, the
forecast has a bias error
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Monitoring & Controlling Forecasts
Tracking
RSFE
signal = MAD
∑(actual demand in
period i forecast demand
in period i)
Tracking
=
signal
(∑|actual - forecast|/n)
What’s the interpretation of a positive or
negative RSFE?
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Tracking Signal
Signal exceeding limit
Tracking signal
+
Upper control limit
Acceptable
range
0 MADs
–
Lower control limit
Time
© 2011 Pearson Education, Inc. publishing as Prentice Hall
Thank You
Questions?
?

Download Report