Professional Documents
Culture Documents
Forecasting
Dr Niniet Indah Arvitrida
Main source:
2
12/10/2020
What is Forecasting ?
Y
Forecasting
Forecasting :
The process of estimating future demand in terms of the
quantity, timing, quality, and location for desired products and
services
Rely on logical methods of manipulating data that have been
generated by historical events for quantitative method
Forecasting is an essential element of capital budgeting.
Sales will be
$200 Million!
Everyone needs
forecasting prior to
planning.
4
12/10/2020
Characteristics of forecasting
Forecasts are usually wrong/inaccurate, seldom
correct, and involves error
find the best method
Long-term forecasts are usually less accurate than short-
term forecasts.
Family / grouped / aggregate forecasts are usually more
accurate than item forecast
The further up the supply chain a company is (the further
they are from the customers), the greater the distortion of
information they receive.
Forecast should include a measure of forecast error
5
Assumptions of Forecast
6
12/10/2020
B(4) C(2)
Production System
8
12/10/2020
Customer
order
decoupling
point
ETO
MTO
ATO
MTS
10
12/10/2020
11
11
Forecasting Steps
• Decide what needs to be forecast
• Level of detail, units of analysis (weekly, monthly, etc) & time horizon
required
• Evaluate and analyze appropriate data
• Identify needed data & whether it’s available
• Select and test the forecasting model
• Cost, ease of use & accuracy
• Generate the forecast
• Monitor forecast accuracy over time
12
12
12/10/2020
13
13
14
14
12/10/2020
n
• Mean Absolute Deviation (MAD)
Most popular A
i 1
i Fi
Standard deviation of errors is assumed MAD =
by 1.25 times MAD
n
Assumption: error is normally distributed
n
A Fi
2
• Mean Square Error (MSE) i
Is similar to variance of a random sample (of errors) MSE = i 1
Should be used in tandem with MAD n
Assumption: mean of error is zero
15
16
12/10/2020
17
17
18
12/10/2020
Demand Behavior
Trend
◦ a gradual, long-term up or down movement of demand
◦ Due to population, technology etc
Random variations
◦ movements in demand that do not follow a pattern
Cycle
◦ an up-and-down repetitive movement in demand
◦ Non-annual; multi-year
◦ Due to interactions of factors influencing economy
Seasonal pattern
◦ an up-and-down repetitive movement in demand occurring periodically
◦ Occurs within one year
◦ Due to weather, customs etc
19
19
Random
movement
Time Time
(a) Trend (b) Cycle
Demand
Demand
Time Time
(c) Seasonal pattern (d) Trend with seasonal pattern
20
20
12/10/2020
Forecasting Technique
Forecasting
Models
Moving Exponential
ARIMA Neural Regression Econometrics
average smoothing Decomposition
networks
Holt’s + Winter’s
21
21
Types of Forecasts
Qualitative (Extrinsic) :
◦ requiring no manipulation of data,
◦ used only judgment of the forecaster,
◦ Evaluating factors other than historical data
◦ concern with identifying various factors that can influence
demand
◦ suitable for long term forecasting
Quantitative (Intrinsic) :
◦ no input of judgment,
◦ mechanical procedure that produce quantitative result,
◦ Rely on historical information
◦ using statistical techniques
◦ suitable for short term forecasting
22
22
12/10/2020
23
23
24
24
12/10/2020
1. Qualitative Methods
-in general -
Drawbacks :
Advantages :
– High cost for paying
– No historical data is labour time of the
required. experts
– Involving experts for – Time consuming,
modeling, so the results particularly in building
are quite accurate. the models and selecting
appropriate methods for
validation
25
25
Can be categorized :
Time series methods : focus entirely on pattern, pattern
change, disturbance caused by random influence
◦ Moving average, exponential smoothing, Holts, winter
causal methods : identification and determination of
relationship between the variable to be forecast and other
influencing variable
◦ Regression
26
26
12/10/2020
Demand Components :
Observed demand (O) =
Systematic component (S) + Random component (R)
27
• Additive :
Systematic component = level + trend + seasonal factor
• Mixed :
Systematic component = ( level + trend ) x seasonal factor
28
28
12/10/2020
29
Example : MA(1)
• MA (1) N=1, the more popular term for this is NAIVE METHOD
ORDERS
MONTH PER MONTH FORECAST
Jan 120 -
Feb 90 120
Mar 100 90
Apr 75 100
May 110 75
June 50 110
July 75 50
Aug 130 75
Sept 110 130
Oct 90 110
Nov - 90
30
30
12/10/2020
n
Di
i=1
MAn =
n
where
n = number of periods in
the moving average
Di = demand in period i
31
31
Example : MA(3)
ORDERS MOVING 3
MONTH PER MONTH AVERAGE Di
i=1
Jan 120 – MA3 =
Feb 90 – 3
Mar 100 –
Apr 75 103.3 90 + 110 + 130
= 3
May 110 88.3
June 50 95.0
July 75 78.3 = 110 orders
Aug 130 78.3
for Nov
Sept 110 85.0
Oct 90 105.0
Nov - 110.0
32
32
12/10/2020
Example : MA(5)
ORDERS MOVING
MONTH PER MONTH AVERAGE 5
Jan 120 –
i=1
Di
Feb 90 – MA5 =
Mar 100 –
5
Apr 75 –
90 + 110 + 130+75+50
May 110 – =
June 50 99.0
5
July 75 85.0
Aug 130 82.0 = 91 orders
Sept 110 88.0 for Nov
Oct 90 95.0
Nov - 91.0
33
33
Smoothing Effects
150 –
125 – 5-month
100 –
Orders
75 –
50 – 3-month
Actual
25 –
0– | | | | | | | | | | |
Jan Feb Mar Apr May June July Aug Sept Oct Nov
Month
34
34
12/10/2020
WMAn = Wi Di
i=1
where
Wi = the weight for period i,
between 0 and 100
percent
Wi = 1.00
35
35
= 103.4 orders
36
36
12/10/2020
37
Ft = Dt-1 + (1 - )Ft-1
38
38
12/10/2020
Ft = Dt-1 + (1 - )Ft-1
where:
Ft = forecast for next period
Dt-1 = actual demand for present period
Ft-1 = previously determined forecast for
present period
= weighting factor / smoothing constant /
level smoothing parameter
39
40
12/10/2020
41
41
FORECAST, Ft + 1
PERIOD MONTH DEMAND ( = 0.3) ( = 0.5)
1 Jan 37 37 37
2 Feb 40 37.00 37.00
3 Mar 41 37.90 38.50
4 Apr 37 38.83 39.75
5 May 45 38.28 38.37
6 Jun 50 40.29 41.68
7 Jul 43 43.20 45.84
8 Aug 47 43.14 44.42
9 Sep 56 44.30 45.71
10 Oct 52 47.81 50.85
11 Nov 55 49.06 51.42
12 Dec 54 50.84 53.21
13 Jan – 51.79 53.61
42
42
12/10/2020
70 –
60 – Actual = 0.50
50 –
40 –
Orders
= 0.30
30 –
Larger , more responsive forecast; Smaller ,
20 – smoother forecast
“Best” can be found by Solver
10 – Suitable for relatively stable time series
0– | | | | | | | | | | | | |
1 2 3 4 5 6 7 8 9 10 11 12 13
Month
43
43
44
44
12/10/2020
560
550
Actual
540
Demand 530
Forecast
520
510
500
490
480
1 2 3 4 5Month
6 7 8 9 10
45
45
Ft+τ = St + τGt
D = Actual Demand
S = Intercept (level)
G = Slope (trend)
• More stability is given to the slope estimate which
implies β ≤ α.
• τ is the amount of step ahead forecast
46
46
12/10/2020
350
300
250 Demand
Holt B(0.1)
200 Holt B(0.3)
150
100
1 2 3 4 5 6 7 8 9 10 11 12
47
47
48
12/10/2020
S0 = intercept, G0 = slope
49
49
50
50
12/10/2020
51
51
w1 w2 w3 W4
52
52
12/10/2020
300
250
200
150
100
50
0
M T W T F M T W T F M T W T F M T W T F
53
53
Procedures
54
54
12/10/2020
• Average factors
F 1.37 1.43 1.33 1.48 1.40
corresponding to the
same period of the
season
55
55
56
56
12/10/2020
or
57
57
58
58
12/10/2020
59
59
60
60
12/10/2020
1 II 2766 4274,125
III 2556 4595,125
IV 8253 4968,5
2001 I [22505491
+ 3514 + 5390,375
(2*(1737+2412+7269))]/(2*4)
II 4382 6083
III 4315 6575,375
IV 12035 6509,25
2002 I 5648 6489,5
II 3696 6688,25
III 4843
IV 13097 61
61
62
62
12/10/2020
63
64
12/10/2020
These
constants
are from
the
We obtain the initial estimates of level and trend exactly previous
as in the static case when we deseasonalized the step
demand (deseaso
(S0 = intercept, G0 = slope) nalized
demand-
step)
Note: the Winter’s method can be started from this step, if S0, G0, c1, c2, c3,
and c4 are known in advance 65
65
These
constants
are from
the
previous
St+1 = (Dt+1/ct+1) + (1-)(St+Gt) step
S1 = 0,12250/0,899 + (deseaso
(0,9)(2592.75+226.86) nalized
demand-
step)
66
66
12/10/2020
67
67
68
12/10/2020
St = Lt represents level
Gt = Tt represents trend
Ct = St represents seasonal
τ = n the amount of step ahead forecast
69
69
70
70