Forecasting

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 25

FORECASTING

What is Forecasting?

 Forecasting is the art and science of predicting future


events.
 Forecast is a statement about the future.
 Forecasts can help managers by reducing some of the
uncertainties that cloud the planning horizon, making it
difficult for a manager to plan effectively
Features Common to All Forecasts

 Forecasting techniques generally assume that the same underlying causal


system that existed in the past will continue to exist in the future.
 Forecasts are rarely perfect; predicted values usually differ from actual
results
 Forecasts for group of items tend to be more accurate than forecasts for
individual items.
 Forecast accuracy decreases as the time period covered by the forecast
increases.
Steps in the Forecasting Process

1. Determine the purpose of the forecast and when it will be needed.


2. Establish a time horizon that the forecast must cover.
3. Select a forecasting technique.
4. Gather and analyze the appropriate data and then prepare the
forecast.
5. Monitor the forecast.
Approaches to 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

1. Executives, Opinions-often used as a part of long-range planning and new product


development.
2. Sales Force Composite - is a good source of information because of its direct contrast
with consumers.
3. Consumer Surveys - it can tap information that might not be available elsewhere.
4. Outside Opinion - this may concern advice on political or economic conditions in a
foreign country some other aspects of interest with which an organization lacks
familiarity.
5. Opinions of Managers and Staff - at times, a manger may solicit from a number of
other managers and/or staff.
Approaches to Forecasting

 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

 Is the simplest forecasting technique.


 The advantage of a naive forecast is that it has virtually
no cost, it is quick and easy to prepare because data
analysis is non existent, and it is easy to understand.
 The main disadvantage is its inability to provide highly
accurate forecasts.
Naïve Forecast

 For example, if the demand last week was 200 units, the
naive forecast for the upcoming week is 200 units.
Moving Average

 is useful if we can assume that market demands will stay fairly


steady over time.
 A three-markmoving average is found by simply summing the
demand during the past three months and dividing by 3.
 With each passing month, the most recent month data are
added to the sum of the previous three months' data and the
earliest month is dropped.
Moving Average

 Mathematically, the moving average (which serves as


an estimate of the next period demand) is expressed as:
Moving Average = (∑ Demand in previous n months) / n

where n is the number of periods in the moving average.


Moving Average

 Compute a three-period moving average forecast given the


following demand for cars for the last 5 periods.

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

 Compute a three-period moving average forecast given the


following demand for cars for the last 5 periods.

DEMAND SUPPLY
1 70
2 80
3 65
4 90
5 85
6 80
Weighted Moving Average

 Weight can be used to place more emphasis in recent values,


when there is a trend or pattern.

DEMAND SUPPLY
1 70
2 80
3 65
4 90
5 85
6
Exponential Smoothing

 When there is no trend in the demand for


goods or services, sales are forecasted for Where:
the next period by means of exponential Ft = the new forecast or
smoothing method. forecast for period
 New Forecast = Last Period’s Forecast +∝ Ft-1 = the previous forecast
(Last Period’s actual demand – Last Period’s or forecast for period t-1
forecast
∝ = smoothing constant
Ft = Ft-1 + ∝ (At-1 – Ft-1) At-1 = actual demand or
sales for period t-1
Exponential Smoothing

A car dealer projected a January demand


for 550 Honda V-tech cars. Actual
January demand was 680 and ∝=0.10. Ft = Ft-1 + ∝ (At-1 – Ft-1)
Forecast the demand for February using
Ft = 550 + 0.10 (680 – 550)
the exponential smoothing model.
Ft = 550 + 0.10 (130)
Ft = Unknown Ft = 550 + 13
Ft = 563
Ft-1 = 550
∝ = 0.10
At-1 = 680
FORECAS
PERIOD ACTUAL DEMAND T ERROR
1 50 0 -

2 52 50 2

Activity 4A 3 48 50.20 -2.2

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.

PERIOD (t) ACTUAL DEMAND (y)


1 560
2 120
3 274
4 609
5 390
6 432
7 125
8 365
9 900
10 563
Simple Linear Regression

 The simplest and most widely used of regression involves a linear


relationship between two variables. The objective in linear
regression is to obtain an equation of a straight line that minimizes
the sum of equation vertical deviations of points around the line.
 The least squares line has the equation:
 Yt = a + bX
b=
 Where:
 Yt = Predicted (dependent) variable
a=
 a = value of Yt when x=0

n = number of observations
b = slope of the line
 X = Predictor (independent) variable
Simple Linear Regression

 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

You might also like