Professional Documents
Culture Documents
Supply Chains
Twelfth Edition, Global Edition
Chapter 8
Forecasting
• Forecast
– A prediction of future events used for planning
purposes.
• Time series
– The repeated observations of demand for a service or
product in their order of occurrence
• There are five basic time series patterns
1. Horizontal
2. Trend
3. Seasonal
4. Cyclical
5. Random
• Demand Management
– The process of changing demand patterns using one
or more demand options
• Complementary Products
• Promotional Pricing
• Prescheduled Appointments
• Reservations
• Revenue Management
• Backlogs
• Backorders and Stockouts
E=
CFE Et
MAD =
n n
Measure Value
Error Measures Blank
CFC (Cumulative Forecast Error) −31
MAD (Mean Absolute Deviation) 8.1
MSE (Mean Squared Error) 87.9
Standard Deviation of Errors 9.883
MAPE (Mean Absolute Percent Error) 17.062%
Et
2
5,275
MSE = = = 659.4
n 8
Et − ( −1.875)
2
= = 27.4
n −1
MAPE =
( E t Dt ) (100 )
=
81.3%
= 10.2%
n 8
The company will spend $1,750 next month on advertising for the
product. Use linear regression to develop an equation and a forecast
for this product.
• Naïve forecast
– The forecast for the next period equals the demand
for the current period (Forecast = Dt)
• Horizontal Patterns: Estimating the average
– Simple moving average
– Weighted moving average
– Exponential smoothing
where
Dt = actual demand in period t
n = total number of periods in the average
Ft+1 = forecast for period t + 1
Ft +1 = W1D1 + W2D2 + + Wn Dt − n +1
• Holdout sample
– Actual demands from the more recent time periods in
the time series that are set aside to test different
models developed from the earlier time periods.
CFE CFE
Tracking signal = or
MAD MADt
• Big Data
– Data sets that are so large or complex that traditional
data processing applications are inadequate to deal
with them.
• Big Data is characterized by:
– Volume
– Variety
– Velocity
• Combination forecasts
– Forecasts that are produced by averaging
independent forecasts based on different methods,
different sources, or different data
• Focus forecasting
– A method of forecasting that selects the best forecast
from a group of forecasts generated by individual
techniques.
Source: From Thomas F. Wallace and Robert A. Stahl, Sales Forecasting: A New Approach (Cincinnati, O H: T. E. Wallace
& Company, 2002), p. 112. Copyright © 2002 T.E. Wallace & Company. Used with permission.
a. Forecast the demand for pizza for June 23 to July 14 by using the
simple moving average method with n = 3 then using the weighted
moving average method with weights of 0.50, 0.30, and 0.20, with .50
applying to the most recent demand.
b. Calculate the MAD for each method.
Copyright © 2019 Pearson Education, Ltd. All Rights Reserved
Solved Problem 2 (2 of 3)
52 plus 65 plus 50, over 3 equals left bracket left paranthesis 0.5 times 52 right paranthesis + left
June 16 52 or
55.7 + 65
56. + 50
= 55.7 or 56 (
0.5 52
parantesis ) ( ) (
+ 0.365 right
0.3 times 65 +paranthesis )
0.2 50 + left
= 55.5or
paranthesis
56 0.2
3 times 50 right paranthesis right bracket = 55.5 or 56
56 plus 52 plus 65, over 3 equals left bracket left paranthesis 0.5 times 56 right paranthesis + left
June 23 56 or
57.7 + 52
58. + 65
= 57.7 or 58 (
0.5 56
parantesis ) (
0.3 times ) (
+ 0.352 right )
0.2 65 + left
52 +paranthesis = 56.6or 57 0.2
paranthesis
3 times 65 right paranthesis right bracket = 56.6 or 57
55 plus 56 plus 52, over 3 equals
June 30
55 + 56 + 52
54.3 or 54. = 54.3 or 54 (
parantesis ) ( ) ( )
left bracket left paranthesis 0.5 times 55 right paranthesis + left
0.5 55 + 0.3 56 + 0.2 52 = 54.7or 55
0.3 times 56 right paranthesis +left paranthesis 0.2
3 times 52 right paranthesis right bracket = 54.7 or 55
60 plus 55 plus 56, over 3 equals
July 7
60 + 55 + 56
57.0 or 57. = 57.0 or 57 (
parantesis
) ( ) ( )
left bracket left paranthesis 0.5 times 60 right paranthesis + left
0.5 60 + 0.3 55 + 0.2 56 = 57.7or 58
0.3 times 55 right paranthesis + left paranthesis 0.2
3 times 56 right paranthesis right bracket = 57.7 or 58
For this limited set of data, the weighted moving average method resulted
in a slightly lower mean absolute deviation. However, final conclusions
can be made only after analyzing much more data.
b. Calculate the absolute percentage error for each month from June through
December and the MAD and MAPE of forecast error as of the end of
December.
c. Calculate the tracking signal as of the end of December. What can you say
about the performance of your forecasting method?
Copyright © 2019 Pearson Education, Ltd. All Rights Reserved
Solved Problem 3 (2 of 4)
a.
Current Month, Calculating Forecast for Next Month Forecast for
t Ft +1 = Dt + (1 − )Ft Month t + 1
December 0.2
0.2 (120120
times ) ++ 0.8 (109.3109.3
0.8times ) = 111.4
= 111.4or
or111
111 January
b.
MAD =
Et
=
87
= 12.4 MAPE =
( E t Dt ) (100 )
=
83.7%
= 11.96%
n 7 n 7
Copyright © 2019 Pearson Education, Ltd. All Rights Reserved
Solved Problem 3 (4 of 4)
c. As of the end of December, the cumulative sum of forecast
errors (C F E) is 39. Using the mean absolute deviation
calculated in part (b), we calculate the tracking signal:
CFE 39
Tracking signal = = = 3.14
MAD 12.4
REGRESI
REGRESI
PERAMALAN
PERAMALAN TIME SERIES
TIME SERIES RATA-RATA
RATA-RATA
MOVING
SMOOTHING
SMOOTHIN MOVING AVERAGE
AVERAGE
G
MODEL
MODEL
KUANTITATIF
KUALITATIF
EXPONENTIAL
SMOOTHING
KAUSAL
CAUSAL
SMA Plotting
1000
800
Demand
Demand
600
SMA-3
400 SMA-6
200
0
1 2 3 4 5 6 7 8 9 10 11 12
Minggu
1000
800
Demand
Demand
600
SES 0,1
400
SES 0,6
200
0
1 2 3 4 5 6 7 8 9
Minggu
• Kedua metoda tergantung pada satu parameter. Jika SMA adalah N, jumlah perioda
dalam SMA, sedangkan SES parameternya α , kontanta pemulusan (smoothing
constant)
• Ketika α = 2/(N+1), maka kedua metoda akan memiliki distribusi kesalahan peramalan
yang sama. Ini berarti kedua nya akan memberikan tingkat akurasi yang sama, tetapi
tidak memberikan hasil peramalan yang sama.
• Pada SMA dibutuhkan semua data N masa lalu yang terakhir, sedangkan SES hanya
membutuhkan satu data masa lalu yang terakhir. Hal ini merupakan kelebihan dari
SES dibandingkan dengan SMA
DES plotting
200
150
Demand
Dt
100
Ft
50
0
1 2 3 4 5 6 7 8 9 10 11 12
Minggu
• Konstan ^ ^ ^ d t
t =1
D (t ) = a a= n
^ ^ ^
• Regresi
D (t ) =linier
a + bt Regresi Kuadratis
Dt = a + bt + ct 2
N N N N
N t .d (t ) − d (t ) t d (t ) n n n n
t (t 2) − n t
2 2 4
t =1
t =1
t =1 t =1 t =1
n n
dt − C t
2
^
2t 2t
D (t ) = a + u cos + v sin a= t =1 t =1
N N N
• Siklis
t 1 2 3 4 5 6 7 8 9 10 11 12
dt 140 159 136 157 173 181 177 188 154 179 180 160
Gambar
diagram
Pencar:
𝑏 = 2.57 ≈ 3
n n
dt bt 𝑎 = 𝐷𝑡 − 𝑏. 𝑡ҧ
t =1 t =1
a= − = dt − b.t
N N 𝑎 = 165.33 − 2.57 6.5 = 148.61 ≈ 149
𝐹𝑡 ′ = 149 + 3𝑡
5737. 27
SEE = 1984 − 0.66(182 ) 1984 − 120 .12
12 − 3 a= =
12 12
5737. 27
= = 155 .32
9
= 25. 25 25
dt' = 155 .32 + 2.2t + 0.66t 2
Copyright © 2019 Pearson Education, Ltd. All Rights Reserved
Pemilihan Metoda Terbaik & Hasil
Peramalan
• Metode yang dipilih adalah metode peramalan linier
• Dt' = 149 + 3t
t 13 14 15 16 17 18 19 20 21 22 23 24
Dt' 188 191 194 197 200 203 206 209 212 215 218 221
CFE = Et
Setiap periode, CFE dan MAD di update untuk memperlihatkan error terbaru dan tracking
signal dibandingkan terhadap batasan yang sudah ditentukan
100
Copyright © 2019 Pearson Education, Ltd. All Rights Reserved
101
Tracking Signal
CFE
• TS = ,CFE = Cumulative Forecast Error
MAD
Spread Number of σ W i t h i n C o n t r o l
(number of MAD) L i m i t s
± 1 . 0 ± 0 . 8 0 5 7 . 6 2
± 1 . 5 ± 1 . 2 0 7 6 . 9 8
± 2 . 0 ± 1 . 6 0 8 9 . 0 4
± 2 . 5 ± 2 . 0 0 9 5 . 4 4
± 3 . 0 ± 2 . 4 0 9 8 . 3 6
± 3 . 5 ± 2 . 8 0 9 9 . 4 8
± 4 . 0 ± 3 . 2 0 9 9 . 8 6
103
Copyright © 2019 Pearson Education, Ltd. All Rights Reserved
104
-0,5
-0,9592
-1
-1,3241
-1,5
-1,7499
-2
-2
-2,4510
-2,5 -2,7324
-3
-3
-3,5
-4
-4
-4,5
Series1