Академический Документы
Профессиональный Документы
Культура Документы
Forecasting
1
What is Forecasting?
2
Forecast
3
Sale forecast
4
Uses of Forecasts
5
I see that you will
REMARKS get an A this
semester.
6
Elements of a Good Forecast
Timely
Reliable Accurate
Written
7
How do we Forecast?
8
Steps in the Forecasting Process
“The forecast”
9
quantitative forecasting step:
10
Types of Forecasts
• Judgmental - subjective analysis
• Special Method
11
Judgmental Forecasts
14
Associative Forecasting
y = a + bx
Where
y = predicted (dependent) variable
x = predictor (independent) variable
b = slope of the line
a = value of y when x = 0 (the height of line
at the y intercept)
18
Computing a and b
n n n
n xt yt xt yt
n n
y t x t
b t 1 t 1 t 1
2 a t 1
b t 1
n
n
n n
n xt xt
2
t 1 t 1
19
Linear Model Seems Reasonable
x y xy x2 y2
7 15 105 49 225 Computed
2 10 20 4 100
6 13 78 36 169 relationship
4 15 60 16 225
14 25 350 196 625 50
7 17 119 49 289
132 271 3529 1796 7159
21
Linear Trend Calculation
812 - 6.3(15)
a = = 143.5
5
y = 143.5 + 6.3 t
Sales in week t = 143.5 + 6.3 t
22
Linear Regression
Remember from Statistics
23
Time Series Data
24
Time series
25
Forecast Variations
Irregular
variation
Figure 3-1
Trend
Cyclical
Cycles
Year 01
00
99
Seasonal variations
26
Time Series Data
- Naïve Method
27
Naïve Forecast
Uh, give me a minute....
We sold 250 wheels last
week.... Now, next week we
should sell....
28
Naïve Forecasts
• Uses a single previous value of a time series as the basis
of a forecast.
• Virtually no cost
• Data analysis is nonexistent
• Easily understandable
• Cannot provide high accuracy
– If it were true, future will always be the same as the past
31
Time Series Data
- Averaging
32
Techniques for Averaging
• Exponential smoothing
33
Moving Average
• Moving average – A technique that
averages a number of recent actual values,
updated as new values become available.
n
Ai
Ft = MAn = i=1
Where n
i = an index that corresponds to periods.
n = Number of periods (data points) in the moving
average period.
Ai = Actual value in period i.
MAn = Forecast based on most-recent n periods.
Ft = Forecast for time period t.
34
Example 2: Moving Average
37
Weighted moving average
Moving Average
• Advantage=Easy to compute and easy to
understand
• Disadvantage=All values in the average are
weighted equally
38
Example 3: Weighted Moving Average
• Find weighted moving average using
Fi =0.4Ai-1 + 0.3Ai-2 + 0.2Ai-3 + 0.1Ai-4.
Period i Actual Demand Forecast
1 42
2 40
3 43
4 40
5 41
6 39
7 46
8 44
9 45
10 38
11 40
12 - 39
Solution to Example 3
• Start from F5 (forecast for period 5).
Period i Actual Forecast
Demand
1 42 -
2 40 -
3 43 -
4 40 -
5 41 41.1 = 0.1(42)+.2(40)+.3(43)+.4(40)
6 39 41.0
7 46 40.2
8 44 42.3
9 45 43.3
10 38 44.3
= 0.1(39)+.2(46)+.3(44)+.4(45)
11 40 42.1
12 - 40.8
40
Shown solutions of Example 1, 2, and 3
48
46
44
42
40
38
36
Observed
34 MA
32 WMA
30
1 2 3 4 5 6 7 8 9 10 11 12
41
Exponential Smoothing
• Current forecast = Previous forecast + α(Actual
- Previous forecast)
42
Example 4: Exponential Smoothing
Period (t) Actual (At) Ft (α = 0.1) Error (A-F) Ft ( α = 0.4) Error (A-F)
1 42
2 40
3 43
4 40
5 41
6 39
7 46
8 44
9 45
10 38
11 40
12
43
Solution to Example 4
Ft = Ft-1 + (At-1 - Ft-1) = (1 – )Ft-1 + At-1
• For example: α = 0.1
• A1 = 42 → F2 = 42 (Naïve)
• A2 = 40 → F3 = F2 + α (A2 - F2)
= 42 + 0 .1 × (40 - 42) = 41.8
• A3 = 43 → F4 = F3 + α (A3 - F3)
= 41.8 + 0 .1 × (43 - 41.8) = 41.92
44
Solution to Example 4 (Cont.)
Ft = Ft-1 + (At-1 - Ft-1)
Period (t) Actual (At) Ft (α = 0.1) Error (A-F) Ft ( α = 0.4) Error (A-F)
1 42
2 40 42 -2.00 42 -2
3 43 41.8 1.20 41.2 1.8
4 40 41.92 -1.92 41.92 -1.92
5 41 41.73 -0.73 41.15 -0.15
6 39 41.66 -2.66 41.09 -2.09
7 46 41.39 4.61 40.25 5.75
8 44 41.85 2.15 42.55 1.45
9 45 42.07 2.93 43.13 1.87
10 38 42.36 -4.36 43.88 -5.88
11 40 41.92 -1.92 41.53 -1.53
12 41.73 40.92
45
Picking a Smoothing Constant α
Actual
50
.4
.1
45
Demand
40
35
1 2 3 4 5 6 7 8 9 10 11 12
Period
46
Time Series Data
- Trend – Least Square Method
47
Linear Trend Equation (Least Square)
Ft
Ft = a + b t
0 1 2 3 4 5 t
y - b x
a =
n
• n = Number of periods
• y = Value of the time series
• t = Specified number of time periods from t = 0
49
Example 5:
• Calculate sales for a Purwokerto-based firm over
the last 10 weeks are shown in the following table.
Week (x) y xy x2
1 700 700 1
2 724 1448 4
3 720 2160 9
4 728 2912 16
5 740 3700 25
6 742 4452 36
7 758 5306 49
8 750 6000 64
9 770 6930 81
10 775 7750 100
55 7407 41358 385
50
Solution to Example 5
7407 - 7.51(55)
a = ≈ 699.40
10
y = 699.40 + 7.51x
51
Solution to Example 5 (Cont.)
52
Exercise : Calculate sales for a Purwokerto-based firm, the
last 5 years data are shown in the following table
Note : 1. start point early year (2001) as based year
53
start point as based year
n(XY ) (X ) ( Y )
b
n ( X 2 ) (X ) 2
Y b (X )
a
n
Ŷt = a + bx
54
middle point as based year
In this case the data is divided into two groups. For amounts
of data:
Even, then its score value of X is ..., -5, -3, -1,1,3,5, ...
Odd, then the value of X of his score is ..., -2, -1,0,1,2, ...
a
Y
b
XY
n X 2
Y = a + bx
55
• Coefficient of 'b' shows an increase (if positive)
or decrease (if negative) on the value of the
variable Y per unit of time.
• For data that the number of odd time period,
the value of 'b' indicates the increase / decrease
in the value of 'Y' per period (per year, per
semester, per quarter or per month).
• For a period of time the amount of data is even,
then the value 'b' indicates the increase /
decrease of the value of 'Y' per half period (per
half year, per half of the semester, per quarter
or per half a half months). 56
Time Series Data
-Trend – Moment method
-Semi Average
57
6. Moment Method
Year Y X XY X2
2001 140 0 0 0
n = 5.
I. 774 = 5.a + b(10) ……… 1.548 = 10a + 20b
II. 1.618 =10.a + b(30) ……….. 1.618 = 10a + 30b (-)
-70 = -10b
b=7
Substitution:
b=7 774 = 5a + 10(7)
5a = 774 – 70 = 704
a = 704/5 = 140,8
In this method:
1. The data is devided into two groups.
2. Basic year is in the middle of the first group.
3. In each group determine the score for X, semi total, and semi
average.
4. The hint is in the first group. If the first group consist of total
odd numbers, so score x = …-4,-3,-2,-1,0,1,2,3,4….but if the
first group consist of total whole even numbers, score x =
.….-5,-3,-1,1,3,5…..
5. Total score x in the first group has to be nil.
6. Then, score for the second group just continue the
first group*.
2005 140 -1
2006 148 0 445 445/3=148,33
2007 157 1
2008 157 2
2009 160 3 486 486/3=162
2010 169 4
a = 148,33
b = 162 148,33 4,5567
3
2006 120 1
2007 125 3
2010 160 9
2011 175 11
a = 116,25
b = 155 116,25= 4,84
2( 4)
equation: Y = 116,25 + 4,84 X
Forecst 2012 (X = 13)
Y2012 = 116,25 + 4,84 (13) = 179 unit.
If the trend line will be shown in graph, the data as follow:
Y2004 = 116,25 + 4,84 (-3) = unit.
Y2005 = 116,25 + 4,84 (-1) = unit.
Y2006 = 116,25 + 4,84 (1) = unit.
Y2007 = 116,25 + 4,84 (3) = unit.
Y2008 = 116,25 + 4,84 (5) = unit.
Y2009 = 116,25 + 4,84 (7) = unit.
Y2010 = 116,25 + 4,84 (9) = unit.
Y2011= 116,25 + 4,84 (11) = unit.
Example for 7 years data
sales for MINA company
2003 130 1
2004#) 145 3
2006 160 7
2007 165 9
• a = 130
• b = 155 130 = 3,125
2( 4)
• Equation trend: Y = 130 + 3,125X
• For 2008 , X = 11
• Y2008 = 130 + 3,125 (11) = 164,375
Determine trend
n(XY ) (X ) ( Y )
b
n ( X 2 ) (X ) 2
Y b (X )
a
n
Year X Y XY X2 Y2
Demand
Year x xy x
industry
2009 12.000 -3 -36.000 9
2010 11.000 -2 -22.000 4
2011 13.000 -1 -13.000 1
2012 14.000 0 0 0
2013 13.000 1 13.000 1
2014 15.000 2 30.000 4
2015 16.000 3 48.000 9
total 94000 0 20.000 28
ΣY ΣXY
a b
n ΣX 2
calculation :
94.000
a 13.428,57143 13.428.571 kw
7
20.000
b 714,2857143 714.286 kw
28
Y’ = a + bx
Y’= 13.428.571 + 714.286x
forecast for industry’s demand :
Y’2016 = 13.428.571 + 714.286(4) = 16.285.715 kw.
Forecast for company’s sales
If company satisfied with averge market share within the
lastest 3 years:
• 2013 = 1.430.000 : 13.000.000 = 0,11
• 2014 = 1.800.000 : 15.000.000 = 0,12
• 2015 = 2.080.000 : 16.000.000 = 0,13
Total MS = 0,36
Average MS = 0,12
forecast company’s sales 2016:
=0,12 X 16.285.715 kw
= 1.954.285,8 kw = 1.954.286 kw.
Exercise : Calculate the sales forecast for 2015 with Least
Square Methode.
The last 5 years data are shown in the following table
Note : 1. start point early year (2010) as based year
Sales (Y)
Year (in unit)
2010 108
2011 119
2012 110
2013 122
2014 130
total
84
Calculate the forecast for 2016 if middle point years
as based year !
(Trend Least Square Methode)
Sales (Y)
Year (in unit)
2010 108
2011 119
2012 110
2013 122
2014 130
2015 131
total
85