Forecasting
Forecasting
Forecasting
What is Forecasting?
Qualitative Forecast
Forecasts based on judgment and opinion
A. Judgmental Forecasts - rely on analysis of subjective inputs
obtained from various sources, such as consumer surveys, the
sales staff, managers, and executives, panels of experts.
Judgmental Forecasts
Quantitative Forecast
Forecast based on historical data
A. Naïve Forecast
B. Moving Average
C. Weighted Moving Average
D. Exponential Smoothing
E. Trend Line Forecast
F. Simple Linear Regression
Naïve Forecast
For example, if the demand last week was 200 units, the
naive forecast for the upcoming week is 200 units.
Moving Average
DEMAND SUPPLY
1 70
2 80
3 65
4 90
5 85
DEMAND SUPPLY
1 70
2 80
Moving Average 3 65
4 90
5 85
Moving Average = (∑ Demand in previous n months) / n
= (65 + 90 + 85)/3
= 240/3
= 80
Moving Average
DEMAND SUPPLY
1 70
2 80
3 65
4 90
5 85
6 80
Weighted Moving Average
DEMAND SUPPLY
1 70
2 80
3 65
4 90
5 85
6
Exponential Smoothing
2 52 50 2
4 51 49.98 1.02
5 50
6 54
Use exponential smoothing model 7 52
to develop a series of forecast for 8 50
the following data and compute the 9 55
10 53
error. 11
(Error = actual - forecast)
A. Use a smoothing factor of 0.10
B. Use a smoothing factor of 0.40 Ft = Ft-1 + ∝ (At-1 – Ft-1) Ft = Ft-1 + ∝ (At-1 – Ft-1)
Ft = 50 + 0.10 (52 – 50) Ft = 50.2 + 0.10 (48 – 50.2)
Ft = 50 + 0.10 (2) Ft = 50.2 + 0.10 (-2.2)
Ft = 50 + 0.2 Ft = 50.2 + (-0.22)
Ft = 50.2 Ft = 49.98
Example:
The total sales of television sets of a
Manila-based firm over the last 10 weeks is
Trend Line Forecast shown in the following table. Determine
the equation of the line and predict the sale
for weeks 11 and 12.
Yt = a + bt
Where ACTUAL
PERIOD DEMAND
Yt = forecast for the period t
(t) (y)
a = value of Yt at t=0 1 800
b = slope of the line 2 810
3 830
t = specified number of time periods from
t=0
4 820
b= 5 850
6 810
a=
7 825
n = number of periods; 8 840
y = value of the time series 9 805
10 830
b= a=
b= a=
a=
b= a=
Trend Line Forecast b = = 1.6 a=
PERIOD ACTUAL
(t) DEMAND (y) ty t2
1 800 800 1
2 810 1620 4
Sale for Week 11 and 12
3 830 2490 9 Yt = a + bt
4 820 3280 16 Yt = + 1.6t
5 850 4250 25
6 810 4860 36 t=11
7 825 5775 49 Yt = + 1.6(11)
8 840 6720 64 Yt =
9 805 7245 81
10 830 8300 100 t=12
Yt = + 1.6(12)
∑ t = 55 ∑ y = 8,220 ∑ ty=45,340 ∑ t2 =385 Yt =
Activity 4B
The total sales of smartphones of SomeSong over the last 10 weeks is shown in the following table.
Determine the equation of the line and predict the sale for weeks 11 to 15.
McdoLibee has a chain of stores in Pangasinan. Sales figures and profiles are given
in the following table. Obtain a regression line for the data and predict profit for a
store assuming sales of 30 million.
Sales, x (Millions) Profit, y (Millions)
15 8
17 9
21 13
18 10
19 11
22 14
16 8.5
17 10
25 15
20 13
Simple Linear Regression
Sales, x Profit, y
xy x2
(Millions) (Millions) b= a=
15 8 120 225 b= a=
b=
17 9 153 289
b = = 0.78
a=
21 13 273 441 a = = -3.67
18 10 180 324
19 11 209 361
22 14 308 484
16 8.5 136 256 Yt = a + bX
17 10 170 289
Y30 = -3.67 + 0.78(30)
25 15 375 625
20 13 260 400 Y30 = -3.67 + 23.4
∑x=190 ∑y=111.5 ∑xy=2184 ∑x2=3694 Y30 = 19.73 million
Activity 4C
Profit, y
Sales, x (Thousand)
(Thousand)
Best TEA has stores in Alaminos 28 10
City that offers hot and cold 32 12
beverages. Sales figures and 37 14
profiles are given in the following 44 34
16 6
table. Obtain a regression line for
34 21
the data, and predict profit for the 32 26
store assuming sales of P500 22 12
thousand. 12 5
41 32