FORECASTING

E LE C3 _ LM4 – F O RE CA ST I N G

R O N A LD A RBO LED A
C AV I T E STAT E U N I V ER S I TY
QUANTITATIVE Methods: Overview
1. Naive approach
2. Moving averages Time-Series
3. Exponential smoothing Models

4. Trend projection
Associative
5. Linear regression Model
EXPONENTIAL SMOOTHING
• Form of weighted moving average
 Weights decline exponentially
 Most recent data weighted most
• Requires smoothing constant ()
 Ranges from 0 to 1
 Subjectively chosen
• Involves little record keeping of past data
EXPONENTIAL SMOOTHING
New forecast = last period’s forecast + a (last period’s actual
demand – last period’s forecast)

Ft = Ft – 1 + a(At – 1 - Ft – 1)

Where: Ft = new forecast

Ft – 1 = previous forecast
a = smoothing (or weighting) constant (0  a  1)
EXPONENTIAL SMOOTHING:
Example
Predicted demand = 142 Ford Mustangs
Actual demand = 153
Smoothing constant (a) = 0.20
EXPONENTIAL SMOOTHING:
Example
Predicted demand = 142 Ford Mustangs
Actual demand = 153
Smoothing constant (a) = 0.20

New forecast = 142 + 0.20 * (153 – 142)

= 142 + 2.2

= 144.2 ≈ 145 cars

EXPONENTIAL SMOOTHING with
TREND ADJUSTMENT
Ft = a(At - 1) + (1 - a)(Ft - 1 + Tt - 1)

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

Step 1: Compute Ft

Step 2: Compute Tt

Step 3: Calculate the forecast FITt = Ft + Tt

EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
Month (t) Actual Demand Smoothed Forecast Smoothed Trend Forecast including
(At) (Ft) (Tt) Trend (FITt)
1 12 11 2 13
2 17
3 20
4 19
5 24
6 21
7 31
8 28
9 36
10
EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
Month (t) Actual Demand Smoothed Forecast Smoothed Trend Forecast including
(At) (Ft) (Tt) Trend (FITt)
1 12 11 2 13
2 17 12.8
3 20
4 19
5 24 Step 1: Forecast for Month 2
6 21
7 31
F2 = aA1 + (1 - a)(F1 + T1)
8 28 F2 = (.2)(12) + (1 - .2)(11 + 2)
9 36
= 2.4 + 10.4 = 12.8 units
10
EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
Month (t) Actual Demand Smoothed Forecast Smoothed Trend Forecast including
(At) (Ft) (Tt) Trend (FITt)
1 12 11 2 13
2 17 12.8 1.92
3 20
4 19
5 24
6 21
Step 2: Trend for Month 2
7 31 T2 = b(F2 - F1) + (1 - b)T1
8 28
T2 = (.4)(12.8 - 11) + (1 - .4)(2)
9 36
10 = .72 + 1.2 = 1.92 units
EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
Month (t) Actual Demand Smoothed Forecast Smoothed Trend Forecast including
(At) (Ft) (Tt) Trend (FITt)
1 12 11 2 13
2 17 12.8 1.92 14.72
3 20
4 19 Step 3: Calculate FIT for Month 2
5 24
6 21
FIT2 = F 2 + T1
7 31 FIT2 = 12.8 + 1.92
8 28
= 14.72 units
9 36
10
EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
Month (t) Actual Demand Smoothed Forecast Smoothed Trend Forecast including
(At) (Ft) (Tt) Trend (FITt)
1 12 11 2 13
2 17 12.8 1.92 14.72
3 20 15.18 2.10 17.28
4 19 17.82 2.32 20.14
5 24 19.91 2.23 22.14
6 21 22.51 2.38 24.89
7 31 24.11 2.07 26.18
8 28 27.14 2.45 29.59
9 36 29.28 2.32 31.60
10 Table 4.1
32.48 2.68 35.16
EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
35 –

30 –
Product demand
25 –

20 –

15 –

10 –

5 –

0 – | | | | | | | | |
1 2 3 4 5 6 7 8 9
Time (month)
EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
35 –
Actual demand (At)
30 –
Product demand
25 –

20 –

15 –

10 –

5 –

0 – | | | | | | | | |
1 2 3 4 5 6 7 8 9
Time (month)
EXPONENTIAL SMOOTHING with TREND
ADJUSTMENT: Example (@ a = 0.20, b = 0.40)
35 –
Actual demand (At)
30 –
Product demand
25 –

20 –

15 –

10 –
Forecast including trend (FITt)

5 –

0 – | | | | | | | | |
1 2 3 4 5 6 7 8 9
Time (month)
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
 LEAST SQUARE METHOD
Values of Dependent Variable

Actual observation
(y value)

Time period
 LEAST SQUARE METHOD
Values of Dependent Variable

Trend line,^ y = a + bx

Time period
 LEAST SQUARE METHOD
Values of Dependent Variable

Deviation7

Deviation5 Deviation6

Deviation3

Deviation4

Deviation1
Deviation2

Time period
 LEAST SQUARE METHOD
Values of Dependent Variable

Actual observation Deviation7

(y value)

Deviation5 Deviation6

Deviation3 Least squares method

minimizes the sum of
Deviation4
the squared errors
(deviations)
Deviation1
Deviation2
Trend line, y^ = a + bx

Time period
LEAST SQUARES METHOD
Equations to calculate the regression variables

^
y = a + bx

Sxy - nxy
b=
Sx2 - nx2

a = y - bx
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) x2 x*y
1999 1 74
2000 2 79
2001 3 80
2002 4 90
2003 5 105
2004 6 142
2005 7 122
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) x2 x*y
1999 1 74 1 74
2000 2 79 4 158
2001 3 80 9 240
2002 4 90 16 360
2003 5 105 25 525
2004 6 142 36 852
2005 7 122 49 854
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) x2 x*y
1999 1 74 1 74
2000 2 79 4 158
2001 3 80 9 240
2002 4 90 16 360
2003 5 105 25 525
2004 6 142 36 852
2005 7 122 49 854
∑x = 28 ∑y = 692 ∑x2 = 140 ∑xy = 3,063
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) x2 x*y
1999 1 74 1 74
2000 2 79 4 158
2001 3 80 9 240
2002 4 90 16 360
2003 5 105 25 525
2004 6 142 36 852
2005 7 122 49 854
∑x = 28 ∑y = 692 ∑x2 = 140 ∑xy = 3,063
x=4 y = 98.86
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) x2 x*y
∑xy - nxy
1999 1 74 1 74 b =
2000 2 79 4 158 ∑x2 - nx2
2001 3 80 9 240
3,063 - (7)(4)(98.86)
2002 4 90 16 360 =
2003 5 105 25 525 140 - (7)(42)
2004 6 142 36 852 = 10.54
2005 7 122 49 854
∑x = 28 ∑y = 692 ∑x2 = 140 ∑xy = 3,063
x=4 y = 98.86
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) x2 x*y
∑xy - nxy
1999 1 74 1 74 b =
2000 2 79 4 158 ∑x2 - nx2
2001 3 80 9 240
3,063 - (7)(4)(98.86)
2002 4 90 16 360 =
2003 5 105 25 525 140 - (7)(42)
2004 6 142 36 852 = 10.54
2005 7 122 49 854
∑x = 28 ∑y = 692 ∑x2 = 140 ∑xy = 3,063
x=4 y = 98.86 a = y - bx
= 98.86 - 10.54(4)
= 56.70
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) x2 x*y
∑xy - nxy
1999 1 74 1 74 b =
2000 2 79 4 158 ∑x2 - nx2
2001 3 80 9 240
3,063 - (7)(4)(98.86)
2002 4 90 16 360 =
2003 5 105 25 525 140 - (7)(42)
2004 6 142 36 852 = 10.54
2005 7 122 49 854
∑x = 28 The
∑y = 692 trend
∑x2 =line
140 is ∑xy = 3,063
x=4 y = 98.86 a = y - bx
y^ = 56.70 + 10.54x = 98.86 - 10.54(4)
= 56.70
 LEAST SQUARES METHOD:
Example
Time Electrical Power
Year Period (x) Demand (y) ^y Using the trend line:
1999 1 74 68
2000 2 79 78 y^= 56.70 + 10.54x
2001 3 80 89
2002 4 90 99
2003 5 105 110
2004 6 142 120
2005 7 122 131
2006 8 142
2007 9 152
LEAST SQUARES METHOD:
Example
160 – Actual Demand
150 –
140 –
Power demand

130 –
120 –
110 –
100 –
90 –
80 –
70 –
60 –
50 –
| | | | | | | | |
1999 2000 2001 2002 2003 2004 2005 2006 2007
Year
LEAST SQUARES METHOD:
Example
160 – Actual Demand
150 –
140 –
Power demand

130 –
120 –
110 –
100 –
90 – Trend line,
80 – y^ = 56.70 + 10.54x
70 –
60 –
50 –
| | | | | | | | |
1999 2000 2001 2002 2003 2004 2005 2006 2007
Year
LEAST SQUARES METHOD
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
ASSOCIATIVE FORECASTING
Used when changes in one or more independent variables can
be used to predict the changes in the dependent variable
Most common technique is linear regression analysis
We apply this technique just as we did in the time series
example
CORRELATION
 How strong is the linear relationship between the variables?
 Correlation does not necessarily imply causality!
 Coefficient of correlation, r, measures degree of association
Values range from -1 to +1

nSxy - SxSy
r=
[nSx2 - (Sx)2][nSy2 - (Sy)2]
CORRELATION
y

(a) Perfect positive x

correlation:
r = +1
CORRELATION
y y

(a) Perfect positive x (b) Positive correlation: x

correlation:
r = +1 0<r<1
CORRELATION
y y

(a) Perfect positive x (b) Positive correlation: x

correlation:
r = +1 0<r<1

(c) No correlation: x
r=0
CORRELATION
y y

(a) Perfect positive x (b) Positive correlation: x

correlation:
r = +1 0<r<1

y y

(c) No correlation: x (d) Perfect negative x

r=0 correlation:
r = -1
COLLABORATIVE PLANNING,
FORECASTING AND REPLENISHMENT
• Collaborative Planning, Forecasting and Replenishment (CPFR) is an
approach which aims to enhance supply chain integration by
supporting and assisting joint practices.

• This allows for continuous updating of inventory and upcoming

requirements, making the end-to-end supply chain process more
efficient.
CPFR Model
CPFR Process