17-09-2024

Outline
Forecasting
4 ▶ Global Company Profile:
Walt Disney Parks & Resorts
▶ What Is Forecasting?
▶ The Strategic Importance of
Forecasting
▶ Seven Steps in the Forecasting
System
▶ Forecasting Approaches

4-1 4-2

1 2

Outline - Continued Learning Objectives

▶ Time-Series Forecasting When you complete this chapter you
▶ Associative Forecasting Methods: should be able to :
Regression and Correlation Analysis 1. Understand the three time horizons and
▶ Monitoring and Controlling Forecasts which models apply for each use
▶ Forecasting in the Service Sector 2. Explain when to use each of the four
qualitative models
3. Apply the naive, moving average,
exponential smoothing, and trend
methods

4-3 4-4

3 4

1
 17-09-2024

Learning Objectives Forecasting Provides a

Competitive Advantage for Disney
When you complete this chapter you
should be able to :
► Global portfolio includes parks in Hong Kong,
4. Compute three measures of forecast Paris, Tokyo, Orlando, and Anaheim
accuracy
► Revenues are derived from people – how
5. Develop seasonal indices many visitors and how they spend their
6. Conduct a regression and correlation money
analysis ► Daily management report contains only the
7. Use a tracking signal forecast and actual attendance at each park

4-5 4-6

5 6

Forecasting Provides a Forecasting Provides a

Competitive Advantage for Disney Competitive Advantage for Disney

► Disney generates daily, weekly, monthly, ► 20% of customers come from outside the
annual, and 5-year forecasts USA
► Forecast used by labor management, ► Economic model includes gross domestic
maintenance, operations, finance, and park product, cross-exchange rates, arrivals into
scheduling the USA
► Forecast used to adjust opening times, rides, ► A staff of 35 analysts and 70 field people
shows, staffing levels, and guests admitted survey 1 million park guests, employees, and
travel professionals each year

4-7 4-8

7 8

2
 17-09-2024

Forecasting Provides a What is Forecasting?

Competitive Advantage for Disney
► Process of predicting a
future event
► Inputs to the forecasting model include airline
specials, Federal Reserve policies, Wall
► Underlying basis
of all business
??
Street trends, vacation/holiday schedules for
3,000 school districts around the world decisions
► Average forecast error for the 5-year forecast ► Production
is 5% ► Inventory
► Average forecast error for annual forecasts is ► Personnel
between 0% and 3%
► Facilities
4-9 4 - 10

9 10

Forecasting Time Horizons Distinguishing Differences

1. Short-range forecast
► Up to 1 year, generally less than 3 months 1. Medium/long range forecasts deal with more
► Purchasing, job scheduling, workforce levels, comprehensive issues and support
job assignments, production levels management decisions regarding planning
and products, plants and processes
2. Medium-range forecast
► 3 months to 3 years
2. Short-term forecasting usually employs
different methodologies than longer-term
► Sales and production planning, budgeting forecasting
3. Long-range forecast 3. Short-term forecasts tend to be more
► 3+ years accurate than longer-term forecasts
► New product planning, facility location,
research and development
4 - 11 4 - 12

11 12

3
 17-09-2024

Influence of Product Life Product Life Cycle

Cycle Introduction Growth Maturity Decline

Best period to Practical to change Poor time to Cost control

Introduction – Growth – Maturity – Decline increase market
share
price or quality
image
change image,
price, or quality
critical

Company Strategy/Issues
R&D engineering is Strengthen niche Competitive costs
► Introduction and growth require longer critical become critical
Defend market
forecasts than maturity and decline Internet search engines
position Drive-through
restaurants

► As product passes through life cycle, Xbox 360

DVDs
iPods
forecasts are useful in projecting Boeing 787
Sales
► Staffing levels 3D printers

► Inventory levels 3-D game Electric vehicles

Analog
TVs
players
► Factory capacity
Figure 2.5
4 - 13 4 - 14

13 14

Product Life Cycle Types of Forecasts

Introduction Growth Maturity Decline

Product design and

development
Forecasting critical Standardization Little product
differentiation
1. Economic forecasts
Product and Fewer product
critical
Frequent product
process reliability changes, more
minor changes
Cost
minimization ► Address business cycle – inflation rate, money
Competitive
and process supply, housing starts, etc.
OM Strategy/Issues

product Optimum capacity Overcapacity in

design changes improvements and the industry
Increasing stability
Short production
runs
options
Increase capacity
of process Prune line to
eliminate items
2. Technological forecasts
Long production
High production not returning
costs
Shift toward
product focus
runs
good margin ► Predict rate of technological progress
Product
Limited models Enhance improvement and Reduce
Attention to quality distribution cost cutting capacity ► Impacts development of new products
3. Demand forecasts
► Predict sales of existing products and services

Figure 2.5
4 - 15 4 - 16

15 16

4
 17-09-2024

Strategic Importance of Seven Steps in Forecasting

Forecasting 1. Determine the use of the forecast
2. Select the items to be forecasted
► Supply-Chain Management – Good
supplier relations, advantages in product 3. Determine the time horizon of the
innovation, cost and speed to market forecast
► Human Resources – Hiring, training, 4. Select the forecasting model(s)
laying off workers 5. Gather the data needed to make the
► Capacity – Capacity shortages can result forecast
in undependable delivery, loss of
customers, loss of market share
6. Make the forecast
7. Validate and implement results
4 - 17 4 - 18

17 18

The Realities! Forecasting Approaches

Qualitative Methods
► Forecasts are seldom perfect,
unpredictable outside factors may ► Used when situation is vague and
impact the forecast little data exist
► Most techniques assume an ► New products
underlying stability in the system
► New technology
► Product family and aggregated
► Involves intuition, experience
forecasts are more accurate than
individual product forecasts ► e.g., forecasting sales on Internet

4 - 19 4 - 20

19 20

5
 17-09-2024

Forecasting Approaches Overview of Qualitative Methods

Quantitative Methods
1. Jury of executive opinion
► Used when situation is ‘stable’ and
historical data exist ► Pool opinions of high-level experts,
sometimes augment by statistical
► Existing products models
► Current technology 2. Delphi method
► Involves mathematical techniques ► Panel of experts, queried iteratively
► e.g., forecasting sales of color
televisions
4 - 21 4 - 22

21 22

Overview of Qualitative Methods Jury of Executive Opinion

► Involves small group of high-level experts
and managers
3. Sales force composite
► Group estimates demand by working
► Estimates from individual salespersons together
are reviewed for reasonableness, then
aggregated ► Combines managerial experience with
statistical models
4. Market Survey ► Relatively quick
► Ask the customer
► ‘Group-think’
disadvantage

4 - 23 4 - 24

23 24

6
 17-09-2024

Delphi Method Sales Force Composite

► Iterative group
process, continues Decision Makers
(Evaluate responses ► Each salesperson projects his or her
until consensus is and make decisions) sales
reached
► Combined at district and national
► 3 types of Staff
(Administering levels
participants survey)

► Decision makers
► Sales reps know customers’ wants
► Staff ► May be overly optimistic
► Respondents Respondents
(People who can make
valuable judgments)
4 - 25 4 - 26

25 26

Market Survey Overview of Quantitative

Approaches
► Ask customers about purchasing
plans 1. Naive approach
► Useful for demand and product 2. Moving averages
design and planning 3. Exponential Time-series
smoothing models
► What consumers say, and what they
actually do may be different 4. Trend projection
5. Linear regression Associative
► May be overly optimistic model

4 - 27 4 - 28

27 28

7
 17-09-2024

Time-Series Forecasting Time-Series Components

► Set of evenly spaced numerical data

Trend Cyclical
► 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 Seasonal Random
future

4 - 29 4 - 30

29 30

Components of Demand Trend Component

Trend
component
► Persistent, overall upward or
downward pattern
Demand for product or service

Seasonal peaks

► Changes due to population,

Actual demand
line technology, age, culture, etc.
Average demand
► Typically several years duration
over 4 years

Random variation
| | | |
1 2 3 4
Time (years)
Figure 4.1

4 - 31 4 - 32

31 32

8
 17-09-2024

Seasonal Component Cyclical Component

► Regular pattern of up and down
fluctuations ► Repeating up and down movements
► Affected by business cycle, political,
► Due to weather, customs, etc.
and economic factors
► Occurs within a single year
► Multiple years duration
PERIOD LENGTH
Week
“SEASON” LENGTH
Day
NUMBER OF “SEASONS” IN PATTERN
7
► Often causal or
Month Week 4 – 4.5 associative
Month Day 28 – 31
relationships
Year Quarter 4
Year Month 12
Year Week 52
0 5 10 15 20
4 - 33 4 - 34

33 34

Random Component Naive Approach

► Erratic, unsystematic, ‘residual’
► Assumes demand in next
fluctuations
period is the same as
► Due to random variation or unforeseen demand in most recent period
events ► e.g., If January sales were 68, then
► Short duration February sales will be 68
and nonrepeating ► Sometimes cost effective and
efficient
► Can be good starting point
M T W T
F 4 - 35 4 - 36

35 36

9
 17-09-2024

Moving Average Method Moving Average Example

► MA is a series of arithmetic means MONTH

January
ACTUAL SHED SALES
10
3-MONTH MOVING AVERAGE

► Used if little or no trend February

March
12
13

► Used often for smoothing April

May
16
19
(10 + 12 + 13)/3 = 11 2/3
(12 + 13 + 16)/3 = 13 2/3

► Provides overall impression of data June 23 (13 + 16 + 19)/3 = 16

July 26 (16 + 19 + 23)/3 = 19 1/3
over time August 30 (19 + 23 + 26)/3 = 22 2/3
September 28 (23 + 26 + 30)/3 = 26 1/3

Moving average =
ådemand in previous n periods October 18 (29 + 30 + 28)/3 = 28
(30 + 28 + 18)/3 = 25 1/3
November 16
n December 14 (28 + 18 + 16)/3 = 20 2/3

4 - 37 4 - 38

37 38

Weighted Moving Average Weighted Moving Average

► Used when some trend might be MONTH ACTUAL SHED SALES 3-MONTH WEIGHTED MOVING AVERAGE

present January
February
10
12
► Older data usually less important March 13
April 16 [(3 x 13) + (2 x 12) + (10)]/6 = 12 1/6
► Weights based on experience and May 19
WEIGHTS APPLIED PERIOD
intuition June
July
23
26 3 Last month

August 30 2 Two months ago

(( )(
Weighted å Weight for period n Demand in period n )) September 28 1 Three months ago

18 6 Sum of the weights

moving = October

average å Weights November

December
Forecast for
16this month =
3 x 14
Sales last mo. + 2 x Sales 2 mos. ago + 1 x Sales 3 mos. ago
Sum of the weights

4 - 39 4 - 40

39 40

10
 17-09-2024

Weighted Moving Average Potential Problems With

Moving Average
MONTH ACTUAL SHED SALES 3-MONTH WEIGHTED MOVING AVERAGE
January 10
February 12 ► Increasing n smooths the forecast but
March
April
13
16 [(3 x 13) + (2 x 12) + (10)]/6 = 12 1/6
makes it less sensitive to changes
May 19 [(3 x 16) + (2 x 13) + (12)]/6 = 14 1/3
[(3 x 19) + (2 x 16) + (13)]/6 = 17
► Does not forecast trends well
June 23
July 26 [(3 x 23) + (2 x 19) + (16)]/6 = 20 1/
2 ► Requires extensive historical data
August 30 [(3 x 26) + (2 x 23) + (19)]/6 = 23 5/6
September 28 [(3 x 30) + (2 x 26) + (23)]/6 = 27 1/
2

October 18 [(3 x 28) + (2 x 30) + (26)]/6 = 28 1/3

November 16 [(3 x 18) + (2 x 28) + (30)]/6 = 23 1/3
December 14 [(3 x 16) + (2 x 18) + (28)]/6 = 18 2/3

4 - 41 4 - 42

41 42

Graph of Moving Averages Exponential Smoothing

Weighted moving average
30 – ► Form of weighted moving average
25 – ► Weights decline exponentially
► Most recent data weighted most
Sales demand

20 –

15 – Actual sales
► Requires smoothing constant ()
10 – Moving average
► Ranges from 0 to 1
► Subjectively chosen
5–
|

J
|

F M
| |

A
|

M J
|

J
|

A
| |

S O
|

N
|

D
|
► Involves little record keeping of past
Figure 4.2
Month data
4 - 43 4 - 44

43 44

11
 17-09-2024

Exponential Smoothing Exponential Smoothing

Example
New forecast = Last period’s forecast
+  (Last period’s actual demand Predicted demand = 142 Ford Mustangs
– Last period’s forecast) Actual demand = 153
Smoothing constant  = .20
Ft = Ft – 1 + (At – 1 - Ft – 1)

where Ft = new forecast

Ft – 1 = previous period’s forecast
 = smoothing (or weighting) constant (0 ≤  ≤ 1)
At – 1 = previous period’s actual demand

4 - 45 4 - 46

45 46

Exponential Smoothing Exponential Smoothing

Example Example
Predicted demand = 142 Ford Mustangs Predicted demand = 142 Ford Mustangs
Actual demand = 153 Actual demand = 153
Smoothing constant  = .20 Smoothing constant  = .20

New forecast = 142 + .2(153 – 142) New forecast = 142 + .2(153 – 142)
= 142 + 2.2
= 144.2 ≈ 144 cars

4 - 47 4 - 48

47 48

12
 17-09-2024

Effect of
Smoothing Constants Impact of Different 
▶ Smoothing constant generally .05 ≤  ≤ .50 225 –

▶ As  increases, older values become less Actual  = .5

significant 200 –
demand

Demand
WEIGHT ASSIGNED TO
MOST 2ND MOST 3RD MOST 4th MOST 5th MOST 175 –
RECENT RECENT RECENT RECENT RECENT
SMOOTHING PERIOD PERIOD PERIOD PERIOD PERIOD
CONSTANT ( ) (1 – ) (1 – )2 (1 – )3 (1 – )4  = .1
 = .1 .1 .09 .081 .073 .066 150 – | | | | | | | | |
 = .5 .5 .25 .125 .063 .031 1 2 3 4 5 6 7 8 9
Quarter
4 - 49 4 - 50

49 50

Impact of Different  Choosing 

225 – The objective is to obtain the most
accurate forecast no matter the
Actual  = .5
► demand of 
Chose high values technique
200 –
when underlying average
Demand

is likely to change We generally do this by selecting the

model that gives us the lowest forecast
► Choose low values of 
175 –
error
when underlying average  = .1
is stable|
150 – | | | | | | | | Forecast error = Actual demand – Forecast value
1 2 3 4 5 6 7 8 9 = At – Ft
Quarter
4 - 51 4 - 52

51 52

13
 17-09-2024

Common Measures of Error Determining the MAD

ACTUAL
TONNAGE FORECAST WITH
QUARTER UNLOADED FORECAST WITH  = .10  = .50
Mean Absolute Deviation (MAD) 1 180 175 175

2 168 175.50 = 175.00 + .10(180 – 175) 177.50

MAD =
å Actual - Forecast 3

4
159

175
174.75 = 175.50 + .10(168 – 175.50)

173.18 = 174.75 + .10(159 – 174.75)

172.75

165.88
n 5 190 173.36 = 173.18 + .10(175 – 173.18) 170.44

6 205 175.02 = 173.36 + .10(190 – 173.36) 180.22

7 180 178.02 = 175.02 + .10(205 – 175.02) 192.61

8 182 178.22 = 178.02 + .10(180 – 178.02) 186.30

9 ? 178.59 = 178.22 + .10(182 – 178.22) 184.15

4 - 53 4 - 54

53 54

Determining the MAD Common Measures of Error

ACTUAL FORECAST ABSOLUTE FORECAST ABSOLUTE
TONNAGE WITH DEVIATION WITH DEVIATION
QUARTER UNLOADED  = .10 FOR a = .10  = .50 FOR a = .50
1

2
180

168
175

175.50
5.00

7.50
175

177.50
5.00

9.50
Mean Squared Error (MSE)
3 159 174.75 15.75 172.75 13.75
å(Forecast errors)
2
4 175 173.18 1.82 165.88 9.12
MSE =
5 190 173.36 16.64 170.44 19.56 n
6 205 175.02 29.98 180.22 24.78

7 180 178.02 1.98 192.61 12.61

8 182 178.22 3.78 186.30 4.30

Sum of absolute deviations: 82.45 98.62

Σ|Deviations|
MAD = 10.31 12.33
n

4 - 55 4 - 56

55 56

14
 17-09-2024

Determining the MSE Common Measures of Error

ACTUAL
TONNAGE FORECAST FOR
QUARTER UNLOADED  = .10 (ERROR)2
1 180 175 52 = 25
2
3
168
159
175.50
174.75
(–7.5)2 = 56.25
(–15.75)2 = 248.06
Mean Absolute Percent Error (MAPE)
4 175 173.18 (1.82)2 = 3.31 n
5
6
190
205
173.36
175.02
(16.64)2 = 276.89
(29.98)2 = 898.80
å100 Actual -Forecast
i i
/ Actuali
7 180 178.02 (1.98)2 = 3.92 MAPE = i=1

8 182 178.22 (3.78)2 = 14.29

n
Sum of errors squared = 1,526.52

å(Forecast errors)
2

MSE = = 1,526.52 / 8 = 190.8

n
4 - 57 4 - 58

57 58

Determining the MAPE Comparison of Forecast Error

ACTUAL
TONNAGE FORECAST FOR ABSOLUTE PERCENT ERROR
Rounded Absolute Rounded Absolute
QUARTER UNLOADED  = .10 100(ERROR/ACTUAL) Actual Forecast Deviation Forecast Deviation
Tonnage with for with for
1 180 175.00 100(5/180) = 2.78% Quarter Unloaded  = .10  = .10  = .50  = .50
2 168 175.50 100(7.5/168) = 4.46%
3 159 174.75 100(15.75/159) = 9.90%
1 180 175 5.00 175 5.00
4 175 173.18 100(1.82/175) = 1.05%
2 168 175.5 7.50 177.50 9.50
5 190 173.36 100(16.64/190) = 8.76%
3 159 174.75 15.75 172.75 13.75
6 205 175.02 100(29.98/205) = 14.62%
4 175 173.18 1.82 165.88 9.12
7 180 178.02 100(1.98/180) = 1.10%
5 190 173.36 16.64 170.44 19.56
8 182 178.22 100(3.78/182) = 2.08%
6 205 175.02 29.98 180.22 24.78
Sum of % errors = 44.75%
7 180 178.02 1.98 192.61 12.61
8 182 178.22 3.78 186.30 4.30

MAPE =
åabsolute percent error = 44.75% = 5.59% 82.45 98.62

n 8
4 - 59 4 - 60

59 60

15
 17-09-2024

Comparison of Forecast Error Comparison of Forecast Error

∑ |deviations|
Rounded Absolute Rounded Absolute ∑ (forecast
Rounded errors) 2
Absolute Rounded Absolute
MAD Actual
= Forecast Deviation Forecast Deviation MSE =Tonnage
Actual Forecast Deviation Forecast Deviation

Quarter
Tonnage
Unloaded
n
with
a = .10
for
a = .10
with
 = .50
for
 = .50 Quarter Unloaded
n
with
a = .10
for
a = .10
with
 = .50
for
 = .50
1 For  180
= .10 175 5.00 175 5.00 1 For  180
= .10 175 5.00 175 5.00
2 168 175.5 7.50 177.50 9.50 2 168 175.5 7.50 177.50 9.50
3 159 = 82.45/8
174.75 = 10.31
15.75 172.75 13.75 3 =
159 1,526.54/8
174.75 = 190.82
15.75 172.75 13.75
4 175 173.18 1.82 165.88 9.12 4 175 173.18 1.82 165.88 9.12
5 For  190
= .50 173.36 16.64 170.44 19.56 5 For  190
= .50 173.36 16.64 170.44 19.56
6 205 = 98.62/8
175.02 = 29.98
12.33 180.22 24.78 6 205 175.02
= 1,561.91/8 = 29.98
195.24 180.22 24.78
7 180 178.02 1.98 192.61 12.61 7 180 178.02 1.98 192.61 12.61
8 182 178.22 3.78 186.30 4.30 8 182 178.22 3.78 186.30 4.30
82.45 98.62 82.45 98.62
MAD 10.31 12.33

4 - 61 4 - 62

61 62

Comparison
n
of Forecast Error Comparison of Forecast Error
∑100|deviation
Rounded i|/actualiRounded
Absolute Absolute Rounded Absolute Rounded Absolute
=Actual
MAPE Tonnage i=1 Forecast
with
Deviation
for
Forecast
with
Deviation
for
Actual
Tonnage
Forecast
with
Deviation
for
Forecast
with
Deviation
for
Quarter Unloaded a = .10 n a = .10 a = .50  = .50 Quarter Unloaded  = .10  = .10  = .50  = .50
1 For  180= .10 175 5.00 175 5.00 1 180 175 5.00 175 5.00
2 168 175.5 7.50 177.50 9.50 2 168 175.5 7.50 177.50 9.50
3 159 = 44.75/8
174.75 = 5.59%
15.75 172.75 13.75 3 159 174.75 15.75 172.75 13.75
4 175 173.18 1.82 165.88 9.12 4 175 173.18 1.82 165.88 9.12
5 For 
190= .50 173.36 16.64 170.44 19.56 5 190 173.36 16.64 170.44 19.56
6 205 175.02
= 54.05/8 =29.98
6.76% 180.22 24.78 6 205 175.02 29.98 180.22 24.78
7 180 178.02 1.98 192.61 12.61 7 180 178.02 1.98 192.61 12.61
8 182 178.22 3.78 186.30 4.30 8 182 178.22 3.78 186.30 4.30
82.45 98.62 82.45 98.62
MAD 10.31 12.33 MAD 10.31 12.33
MSE 190.82 195.24 MSE 190.82 195.24
MAPE 5.59% 6.76%
4 - 63 4 - 64

63 64

16
 17-09-2024

Exponential Smoothing with Exponential Smoothing with

Trend Adjustment Trend Adjustment
Forecast Exponentially Exponentially
When a trend is present, exponential including (FITt) = smoothed (Ft) + smoothed (Tt)
smoothing must be modified trend forecast trend

Ft = (At - 1) + (1 - )(Ft - 1 + Tt - 1)
MONTH ACTUAL DEMAND FORECAST (Ft) FOR MONTHS 1 – 5

1 100 Ft = 100 (given) Tt = b(Ft - Ft - 1) + (1 - b)Tt - 1

2 200 Ft = F1 + (A1 – F1) = 100 + .4(100 – 100) = 100

3 300 Ft = F2 + (A2 – F2) = 100 + .4(200 – 100) = 140 where Ft = exponentially smoothed forecast average
4 400 Ft = F3 + (A3 – F3) = 140 + .4(300 – 140) = 204
Tt = exponentially smoothed trend
At = actual demand
5 500 Ft = F4 + (A4 – F4) = 204 + .4(400 – 204) = 282
 = smoothing constant for average (0 ≤  ≤ 1)
b = smoothing constant for trend (0 ≤ b ≤ 1)
4 - 65 4 - 66

65 66

Exponential Smoothing with Exponential Smoothing with

Trend Adjustment Trend Adjustment Example
MONTH (t) ACTUAL DEMAND (At) MONTH (t) ACTUAL DEMAND (At)
Step 1: Compute Ft 1 12 6 21

Step 2: Compute Tt 2 17 7 31

3 20 8 28
Step 3: Calculate the forecast FITt = Ft + Tt 4 19 9 36

5 24 10 ?

 = .2 b = .4

4 - 67 4 - 68

67 68

17
 17-09-2024

Exponential Smoothing with Exponential Smoothing with

Trend Adjustment Example Trend Adjustment Example
TABLE 4.1 Forecast with  - .2 and b = .4 TABLE 4.1 Forecast with  - .2 and b = .4
SMOOTHED FORECAST SMOOTHED FORECAST
FORECAST SMOOTHED INCLUDING TREND, FORECAST SMOOTHED INCLUDING TREND,
MONTH ACTUAL DEMAND AVERAGE, Ft TREND, Tt FITt MONTH ACTUAL DEMAND AVERAGE, Ft TREND, Tt FITt
1 12 11 2 13.00 1 12 11 2 13.00
2 17 12.80 2 17 12.80 1.92
3 20 3 20
4 19
Step 1: Average for Month 2 4 19
5 24 5 24 Step 2: Trend for Month 2
6 21 F2 = A1 + (1 – )(F1 + T1) 6 21
7 31 7 31 T2 = b(F2 - F1) + (1 - b)T1
F2 = (.2)(12) + (1 – .2)(11 + 2)
8 28 8 28
T2 = (.4)(12.8 - 11) + (1 - .4)(2)
9 36 = 2.4 + (.8)(13) = 2.4 + 10.4 9 36
10 — 10 — = .72 + 1.2 = 1.92 units
= 12.8 units
4 - 69 4 - 70

69 70

Exponential Smoothing with Exponential Smoothing with

Trend Adjustment Example Trend Adjustment Example
TABLE 4.1 Forecast with  - .2 and b = .4 TABLE 4.1 Forecast with  - .2 and b = .4
SMOOTHED FORECAST SMOOTHED FORECAST
FORECAST SMOOTHED INCLUDING TREND, FORECAST SMOOTHED INCLUDING TREND,
MONTH ACTUAL DEMAND AVERAGE, Ft TREND, Tt FITt MONTH ACTUAL DEMAND AVERAGE, Ft TREND, Tt FITt
1 12 11 2 13.00 1 12 11 2 13.00
2 17 12.80 1.92 14.72 2 17 12.80 1.92 14.72
3 20 3 20 15.18 2.10 17.28
4 19 4 19 17.82 2.32 20.14
5 24 Step 3: Calculate FIT for Month 2 5 24 19.91 2.23 22.14
6 21 6 21 22.51 2.38 24.89
7 31 FIT2 = F2 + T2 7 31 24.11 2.07 26.18
8 28 8 28 27.14 2.45 29.59
FIT2 = 12.8 + 1.92
9 36 9 36 29.28 2.32 31.60
10 — = 14.72 units 10 — 32.48 2.68 35.16

4 - 71 4 - 72

71 72

18
 17-09-2024

Exponential Smoothing with Trend Projections

Trend Adjustment Example
Fitting a trend line to historical data points to
40 – Figure 4.3
project into the medium to long-range
35 – Actual demand (At)
30 – Linear trends can be found using the least
Product demand

25 – squares technique
20 –
15 – y^ = a + bx
10 – Forecast including trend (FITt) where y^ = computed value of the variable to be predicted
5 – with  = .2 and b = .4 (dependent variable)
a = y-axis intercept
0 – b = slope of the regression line
| | | | | | | | | x = the independent variable
1 2 3 4 5 6 7 8 9
Time (months)
4 - 73 4 - 74

73 74

Least Squares Method Least Squares Method

Values of Dependent Variable (y-values)

Actual observation Deviation7 Equations to calculate the regression variables

(y-value)

Deviation5 Deviation6 ŷ = a + bx
Deviation3
Least squares method minimizes the
sum of Deviation
the squared
4
errors (deviations)

Deviation1
(error) Deviation2
Trend line, y^ = a + bx

|
1
|
2
|
3
|
4
|
5 6
| |
7
a = y - bx
Figure 4.4
Time period
4 - 75 4 - 76

75 76

19
 17-09-2024

Least Squares Example Least Squares Example

ELECTRICAL POWER
YEAR (x) DEMAND (y) x2 xy
ELECTRICAL ELECTRICAL
1 74 1 74
YEAR POWER DEMAND YEAR POWER DEMAND
2 79 4 158
1 74 5 105
3 80 9 240
2 79 6 142
4 90 16 360
3 80 7 122 5 105 25 525
4 90 6 142 36 852
7 122 49 854
Σx = 28 Σy = 692 Σx2 = 140 Σxy = 3,063

x=
å x = 28 = 4 y=
å y = 692 = 98.86
n 7 n 7

4 - 77 4 - 78

77 78

Least Squares Example Least Squares Example

- nxy 3,063 - (7) ( 4) (98.86) 295
å xyELECTRICAL Trend line,
b= = POWER = = 10.54 160 – y^ = 56.70 + 10.54x
YEAR (x) å x - nxDEMAND (y)140 - (7) ( 4 ) x 28
2 2 2 2 xy
150 –
Power demand (megawatts)

1 74 1 74
140 –
()
2 79 4 158
3
a = y - bx = 98.8680
-10.54 4 = 56.70 9 240
130 –
120 –
4 90 16 360
110 –
5 105 ŷ = 56.70 +10.54x25
Thus, 525
100 –
6 142 36 852
90 –
7 122 49 854
Σx = 28 Σy = 692 Σx2 = 140 Σxy = 3,063
80 –
70 –

x=
å x =in28year
Demand
=4
å y+=10.54(8)
8 = 56.70
y=
692
= 98.86
60 –
= 141.02, 50 –
n 7 n or 7141 megawatts | | | | | | | | |
1 2 3 4 5 6 7 8 9
Year Figure 4.5
4 - 79 4 - 80

79 80

20
 17-09-2024

Least Squares Requirements

1. We always plot the data to insure a

linear relationship
2. We do not predict time periods far
beyond the database
3. Deviations around the least squares
line are assumed to be random

4 - 81

81

21