Assignment Method
Assignment Method
1. The assignment problem is the problem of assigning n workers to n jobs, in such a way
that a worker is assigned to only one job. The workers assigned to it and the costs of
completing all of the jobs will be minimized.
2. The assignment method is the standard procedure for solving the assignment problem
on the basis of the assignment table.
1. Subtract the smallest cost from each entry in each row. If each zero can now be
assigned in a one-to-one correspondence with the “workers”, an optional solution is
obtained. If not, go to step 2.
2. Subtract the smallest cost in each column. If the zero entries can now be distributed in
each one corresponding with the “workers”, an optimal solution is obtained or reached. If
not, go to step 3.
3. Cover the zero entries by vertical or horizontal lines, using least numbers of lines
possible. (This can be done by covering first the row or column having the most numbers
of zeros.) Subtract the smallest uncovered cost from each uncovered cost but add it to
the entry found at the intersection of the lines. If an assignment is already possible, an
optional solution is reached. If not, repeat step 3. An assignment is optimum if the
numbers of lines is equal to the numbers of rows or the or the numbers of column
Example 1.
During the foundation Day, the BA Faculty Club’s four representatives participate in
different sports such as walkathon, marathon, swimming, and running. The table below shows
their performance per event (minutes). Determine who among the faculty representatives will
participate in each event.
Since each faculty is allowed to participate in only one event, the assignment method is
the most effective way to find an optimum solution.
Solution:
We start reducing the rows by subtracting the smallest the smallest number in each row
from all the numbers in the row.
Example 2.
The Gayoma Company has three jobs to be done on three machines. Each job must be
done on one and only one machine. The cost of each machine is given next page. Determine
the job assignment which will minimize the cost.
Machines
Jobs
X Y Z
A 1400 1600 1800
B 1200 1300 1400
C 1400 1800 1500
We reduce the given numbers by deleting two zeros, then the new table.
Table 1.
Machines
Jobs
X Y Z
A 14 16 18
B 12 13 14
C 14 18 15
Table 2.
Machines
Jobs
X Y Z
A 0 2 4
B 0 1 2
C 0 4 1
Now reduce each column by subtracting the smallest number in each column.
Table 3.
Machines
Jobs
X Y Z
A 0 1 3
B 0 0 1
C 0 3 0
Since we have three lines that correspond to the number of rows and columns, then it is already
optimal.
Final Decision:
Example 3.
Former UAAP players are about to join the most prestigious league in the country, the
Philippines Basketball Association (PBA). Five teams are willing to acquire the services of the
following players: James Yap, Mark Cadona. Arwind Santos, Ronald Tubid, and Bonbon
Custodio.
TEAMS
Burger Talk N' Purefood Ginebra San
Players King Text s King Miguel
Bonbon
Custodio
200,000 250,000 175,000 210,000 180,000
Ronald
Tubid
250,000 170,000 200,000 180,000 190,000
Arwind
Santos
150,000 210,000 185,000 165,000 200,000
Mark
Cardona
160,000 150,000 175,000 180,000 190,000
James
Yap 175,000 180,000 150,000 200,000 210,000
The table shows the monthly salaries offer including the bonuses and other benefits.
Determine the optimal answer on each team to minimize their costs.
Solution:
To make the computation much easier, we temporarily remove the three zeros.
TEAMS
Burger Talk Ginebra San
Players King N' Text Purefoods King Miguel
Bonbon
Custodio 200 250 175 210 180
Ronald
250 170 200 180 190
Tubid
Arwind
Santos 150 210 185 165 200
Mark
Cardona 160 150 175 180 190
James
Yap 175 180 150 200 210
*Results after removing three zeros in each entry is presented in the above table.
TEAMS
Burger Talk Pure Ginebra San
Players King N' Text foods King Miguel
Bonbon
Custodio 25 75 0 35 5
Ronald
Tubid 80 0 30 10 20
Arwind
Santos 0 60 35 15 50
Mark
Cardona 10 0 25 30 40
James
Yap 25 30 0 50 60
*Results after subtracting the smallest entry in each row is shown in the above table
Since the zeros cannot be assigned to each player, go on to the next step.
TEAMS
Burger Talk Ginebra San
Players King N' Text Purefoods King Miguel
Bonbon
Custodio 25 75 0 35 0
Ronald
Tubid 80 0 30 10 15
Arwind
Santos 0 60 35 15 45
Mark
Cardona 10 0 25 30 35
James
Yap 25 30 0 50 55
*Results after subtracting the smallest entry in each column (columns 5 and 6, Ginebra King
and San Miguel, respectively).
TEAMS
Burger Talk Ginebra San
Players King N' Text Purefoods King Miguel
0
Bonbon
Custodio
25 75 25 0
Ronald
Tubid 80 0 30 0 15
Arwind
Santos 0 60 35 5 45
Mark
Cardona 10 0 25 20 35
James Yap
25 30 0 40 55
Since the number of lines used is equal to the number of rows and columns, assignment is
optimum.
Assigning the teams to the players (giving each zero to each player)
Final Decision:
Total ₱810,000.00
*Covering zero entries with the least number in vertical and horizontal lines.
TEAMS
Burger Talk N' Ginebra
Players King Text Purefoods King San Miguel
Bonbon 25 0
Custodio 25
75 0
Ronald
Tubid 80 0 30 0 15
Arwind
Santos 0
60 35 5 45
Mark
Cardona 10 0 25 20 35
James
Yap 25 30 0 40 55
NAME: __________________________________________DATE:_________________
SECTION/TIME/DAY:_________________________ROOM:_____________RATING________
Exercise 14
1. Five security officers are requested by the University of the East to be assigned in five
buildings. The daily cost of each officer in each building is indicated below. Determine the best
allocation of officers to various buildings so as to minimize the cost.
BUILDINGS
2. Doggy agency has three police dogs to be assigned to three different department stored. The
cost of each dog on each department s given below
Machines A B C D
J 1 300 500 700 900
O 2 300 700 500 700
B 3 900 600 300 300
S 4 800 900 500 500
4. Jacqueline and Vilma are business partners. They decided to hire four accountants to be
assigned to audit their business. The next table shows the cost per accountants. Determine the
best allocation for each accountant.
Accountants 1 2 3 4
5. Former PBL players are about to join the most prestigious league in the country, the
Philippines Basketball Association (PBA). Four teams are willing to acquire the services of the
following players: James Yap, Rich Alvarez, Paul Artadi, and Ronald Tubid. The table below
shows the monthly salaries they wanted excluding the bonuses and other benefits. Determine
the optimal answer for each team to minimize their cost.
Yap Alvarez Artadi Tubid
6. Determine the optimal assignment of the management teams to the four projects
PROJECTS
W X Y Z
1. 3,800 2,800 2,400 3,600
2. 2,000 2,400 3,000 2,000
3. 3,200 1,800 2,200 2,800
4. 4,000 3,200 2,600 3,400
7. The Fast Food lane decided to acquire the services of four part-time students to work as
service crew. They were given a speed test. The table below indicates their performances per
lane. Determine the best allocation for each crew.
Crew 4 17 15 18 19
8. Five workers of Denzel Engineering Works are to be assigned, one each to five machines.
Find the cost of allocation of the variable to the five workers.
WORKERS
Machines A B C D E
1 74 52 66 64 90
2 50 44 78 68 48
3 62 70 52 56 72
4 84 36 56 80 46
5 58 38 76 54 84
9. The V. Mapa High School students are about to join the Annual Quiz Bee to be held at the
PICC. The quiz bee consists of four subjects such as Math, Science, English, and Physics. The
table below shows their errors per subject in the qualifying round. Determine who among the
students will represent in the quiz bee.
10. Miling and Luming Contractors need three carpenters to be assigned to three projects.
Determine the best allocation of each carpenter.
Carpenters A B C
1 80 90 54
2 54 108 30
3 46 104 48
11. Three regular researchers of Mic-Mic Marketing Research are required to submit their
Estimated Project Completion (EPC) times (days) to three clients. The table below shows their
EPC. Determine the best allocation for three researchers.
Clients
Employees 1 2 3
Denzel 20 30 18
Rino 18 36 10
Alvin 12 28 6
CASE STUDY
NHOLRAM-BONG CORPORATION
Table 4.1 shows the production costs for each plant, the variable costs both during regular
time and overtime, and the fixed costs during the operation and non-operation
Table 4.1
NHOLRAM-BONG CORPORATION
Table 4.2 shows the distribution costs from each plant to each warehouse.
Table 4.2
NHOLRAM-BONG CORPORATION
Distribution Center
From Plant W1 W2 W3 W4 W5
If Nholram-Bong down any of its plants, its weekly costs will change as the fixed costs
decrease due to non-operation.
Discussion Questions
1. Evaluate the various conditions that will meet the weekly demand for both operating
and non-operating plants. Determine which condition will minimize the costs.
Chapter 5
Forecasting
Key Terms:
Forecast
Qualitative Method
Quantitative Method
Delphi Method
Jury of Executive Opinion
Sales Force Composite
Consumer Market Survey
Time Series
Time Series Method
Trend
Seasonality
Cycles or Cyclical Components
Random Variations/Irregular Components
Smoothing Method
Smoothing Constant
Weighted Moving Averages
Exponential Smoothing
Trend Projections
Mean Absolute Deviation (MAD)
Mean Squared Error (MSE)
Mean Absolute Percent Error (MAPE)
Trend Line Forecast
Learning Objectives
Introduction
In business of any field, anticipating the needs of your clients and serving these needs,
definitely spell success. A good management team uses past and present data, analyzes the
trend of the current situation, and still relies on “gut feeling” on what is likely to happen in the
future. Decisions are made every day, and coming up with the best strategic plan of action in
the future is an essential tool. Consequently, managers try to minimize the “uncertainty” of the
future in forecasting. A forecast simply means a prediction of what is likely to happen in the
future. Converting the prediction into numbers and concrete data is the main purpose of
forecasting.
What is forecasting?
It is the process of elimination in unknown situations. Prediction is similar, but in a more
general term.
Business forecasting is an estimate or prediction of future development in business such
as sales, expenditures, revenues, income, and profits. It is considered as one of the most
important aspect of corporate planning.
Demand forecasting is a forecast that projects the company’s sales.
Classification of Forecasting
There are two classifications of forecasting methods: Qualitative and Quantitative.
FORECASTING METHODS
Forecasting
Methods
Moving Jury of
Averages
Regression Executive Opinion
Analysis
Trend Consumer
Qualitative Forecast
This type of forecasting method is based on judgements or opinions and is subjective in
nature. It does not rely on mathematical computations.
Types of Qualitative Methods
Delphi Method
One of the most commonly used qualitative forecasting is the Delphi Method. Here, a
group of experts separated from each other makes a forecast. In its usual application, they are
asked to answer questionnaire. These groups are called the “respondents”. The answer and
other data are gathered, collected, summarized by staff personnel and are turned over to
another group, the decision makers or the forecasters. It is important to note that Delphi
Method’s principle is that, responses from the first questionnaires are used and considered in
preparing the second set of questionnaires. Responses are gathered, and the process is
repeated until a consensus of the group is reached.
1. Trend (T) – the gradual shifting (upward or downward movement) of the time series. The
shifting or trend is frequently the result of long term factors such as
1000
800
Series (100000)
600
400
200
0
0 1 2 3 4 5 6
Year
Figure 5.1
Linear Trend of DVD Sales
Figure 5.1 shows a straight line that may be a good approximation of the trend in DVD
sales. When a time series consists of random fluctuation move around a long-term trend line, a
linear equation may be used to estimate the trend. This is shown in Figure 5.2
Figure 5.2
Examples of Some Possible Time Series Trend Patterns
2. Seasonality (S) – is a pattern of the demand fluctuation above or below the trend line that
occurs every year. This is the component of the time series that represents the variability in the
data due to seasonal influences.
3. Cycles or Cyclical Components – any recurring sequence of points above and below the
trend line lasting more than one year. These are usually tied into the business cycle.
Trend line
Time
Figure 5.3
Trend and Cyclical Components of a Time Series
4. Random Variations (R) – “blips” in the data caused by chance and unusual situations and do not
follow discernible pattern.
a. Multiplication Model – assumes that demand is the product of the four components.
Demand = T x S x C x R
b. Additive Model – adds the components together to provide an estimate.
Demand = T + S + C + R
Actual demand
Figure 5.4
Time Series and Its components
Smoothing method
Three more forecasting methods are to be discussed in this section. These methods are
moving averages, weighted moving averages, and exponential smoothing. These methods
“smooth out” random fluctuations caused by irregular components of the time series. They are
best used for stable time series where no movement in trend is expected.
Naïve Method
Naïve forecast is the simplest technique. It simply uses the actual demand for the past
period as the forecasted demand for the next period. This makes the theory that the past will
repeat. It also assumes that any time series components (trend, seasonality or cycles) are either
reflected in the previous period’s demand or do not exist.
Table 5.1
Naïve forecasting
Period Demand Forecast
1 35
2 40 35
3 55 40
4 65 55
5 60 65
Notice the demand on Period 1 was 35, the naïve forecast for the upcoming period is 35.
Moving Averages
These use the average of the most recent n data values in the time series forecast for
the next period.
Formula
Moving Average ¿
∑ ( most recent n data values ) (Table 5.1)
n
Example:
Compute for a four-month moving average using the data given in Table 5.2
This is a smoothing method that uses a weighted average of the recent n data as
the forecast.
Formula:
Example 1.
Compute for a three month weighted moving average (Table 5.3)
Three-Month Weighted Moving Average Forecast
Three-Month Weighted Moving
Month Demand Average
January 21
February 25
March 29
⦋ ( 29 ×3 )+ (25 × 2 )+ 21 ⦌
=26
April 21 6
⦋ ( 21 ×3 ) + ( 29 ×2 )+25 ⦌
=24
May 25 6
⦋ ( 25 ×3 )+ ( 21×2 )+29 ⦌
=24
June 20 6
⦋ ( 20 ×3 )+ ( 25× 2 )+ 21 ⦌
=22
July 18 6
⦋ ( 18 ×3 )+ (20 × 2 )+ 25 ⦌
=20
August 21 6
⦋ ( 21 ×3 ) + ( 18 ×2 ) +20 ⦌
=20
September 20 6
⦋ ( 20 ×3 )+ ( 21×2 )+18 ⦌
=20
October 19 6
⦋ ( 19 ×3 )+ ( 20 × 2 )+ 21 ⦌
=20
November 18 6
⦋ ( 18 ×3 )+ (19 × 2 )+ 20 ⦌
=19
December 15 6
Example 2.
Compute a four-period weighted moving average forecast from Table 5.4
Four-Period Weighted Moving Average Forecast
Period Forecast Three-Month Weighted Moving Average
1 21
2 25
3 29
4 21
⦋ ( 21 ×3 ) + ( 29 ×2 )+25 ⦌
=24
5 25 6
6 75 ⦋ ( 29 ×3 )+ (25 × 2 )+ 21 ⦌
=26
6
Exponential Smoothing
This is a forecasting method that is a combination of the last forecast and the last
observed value. It uses a weighted average of past time series value as the forecast and is
based on the idea that as data gets older it becomes less relevant and should be given less
weight.
Formula:
New forecast = Last period’s forecast
Mathematically:
Where:
F t = new forecast
ɑ = smoothing constant that has a value between 0 and 1 (the Greek letter ɑ is
pronounced ‘alpha’
At −1 = previous period’s actual demand
Example 1.
In January, a demand for 200 units of Toyota car model “Vios” for February was
predicted by a car dealer. Actual February demand was 250 cars. Forecast the March demand
using a smoothing constant of ɑ = 0.30.
Example 2.
Use exponential smoothing to compute for a series of forecast with smoothing constant
of:
a. ɑ = 0.20;
b. ɑ = 0.50; and
c. plot the actual data and both sets on a single graph
Table 5.5
Period Demand
1 20
2 35
3 46
4 40
5 50
6 55
7 45
8
Solution:
a. ɑ = 0.20
Table 5.6
Period Actual Demand Forecast Error
1 20 -
2 35 20 15
3 46 23 23
4 40 27.60 13.60
5 50 30.08 19.92
6 55 34.06 20.94
7 45 38.35 6.75
8 39.60
F 3 = 20 = 0.20(35 - 20)
F 3 = 23
Graph of 0.20
60
50
40
30
20
10
0
1 2 3 4 5 6
50
40
30
20
10
0
1 2 3 4 5 6
Others methods for determining or measuring the accuracy of forecast error are MAD,
MSE, MAPE, and BIAS.
(Forecast errors)
MAD = (6.4)
n
Example 1.
Table 5.8
Period Demand Error at ɑ = 0.20 Error at ɑ = 0.50
1 20
2 35 15 15
3 46 23 18.50
4 40 13.60 3.25
5 50 19.92 11.62
6 55 20.94 10.81
7 45 6.75 -4.59
8
99.21 63.77
MAD = (16.54) MAD = (10.63)
6 6
Based on the computation, the MAD of ɑ = 0.20 is greater than the MAD of ɑ = 0.50.
Thus, the ɑ = 0.50 is preferred because its MAD is smaller.
Mean Squared Error (MSE) is a technique for determining the accuracy of a forecasting
model by taking the average of the squared error terms for a forecasting method.
( Forecasting Error )2
MSE = (6.5)
n
Example 2.
Solution:
a) ɑ = 0.20
Table 5.9
Period Demand Forecast Error Squared Forecast Error
at ɑ = 0.50
1 20
2 35 15 225
3 46 23 342.25
4 40 13.60 10.56
5 50 19.92 135.02
6 55 20.94 116.86
7 45 6.75 21.07
8
850
MSE = = 141.79
6
b) ɑ = 0.50
Table 5.10
Period Demand Forecast Error Squared Forecast Error
at ɑ = 0.20
1 20
2 35 15 225
3 46 23 529
4 40 13.60 184.96
5 50 19.92 396.81
6 55 20.94 438.48
7 45 6.75 45.56
8
1819.81
MSE = = 303.30
6
Based on the computation, the MSE of ɑ = 0.20 is greater than the MSE of ɑ = 0.50.
Thus, the ɑ = 0.50 is preferred because its MSE is smaller.
Mean Absolute Percent Error (MAPE) is a technique for determining the accuracy of a
forecasting method by taking the average of the absolute errors as a percentage of the
observed value
BIAS is a component of total calculated forecast error. It tells whether the forecast is too
low or too high, and by how much. In effect, it provides the total error and its direction.
MAPE =
∑ of Absolute Error (6.6)
∑ of Actual
Mathematically;
MAPE =
∑ ∑ of Absolute Error (6.7)
∑ ( Actual)
Absolute Accuracy = Maximum (0, 1 – MAPE) (6.8)
Example 1.
Table 5.11
Absolu Arithme
Foreca Absolu te tic
Perio Actu Foreca st te Percenta Accura Accurac
d al st Error Error ge Error cy y
a b c d e f g h
Formula b-c abs(d) e/b 1-f
b/c
1 50 45 5 5 10% 90% 111%
2 55 70 -15 15 27% 73% 79%
3 60 60 0 0 0% 100%
4 50 75 -25 25 50% 50% 67%
5 60 80 -20 20 33% 67% 75%
Total 275 330 -55 65 24% 76% 83%
Percentage Error =
∑ ( Absolute Error)
∑ ( Actual)
65
= x 100%
275
= 24%
MAPE =
∑ ( Absolute Error)
∑ Actual x 100 %
65
= x 100%
275
= 24%
= 76%
This technique fits a trend line to a series of historical data points and then projects the
line in the future for medium to long range forecast (we focused on straight line trends only).
The common statistical method to be used is known as the Least Squares Method.
The Least Squares Method finds a straight line that minimizes the sum of the vertical
differences from the line to each of the data points.
T 1 = a + bt x (6.9)
Where:
T t = computed value of the variable to be predicted (dependent variable)
a = intercept of the trend line (Y-axis intercept)
b = slope of the trend line
t x = independent variable
The formula in computing a and b is:
b=
∑ ty−nty (6.10)
∑ t2−nt2
∑ = Summation sign for n data points
t = Values of the independent variables
Y = Values of the dependent variables
T = Average of the values of the X’s
Ῡ = Average of the values of the Y’s
n = number of data points or observations
a = Ῡ - bt (6.11)
Example:
13.25
b= = 0.22
60
Since we have already solved the corresponding variables for trend equation, the new equation
is T 1 = 3.41 + 0.22t.
We can now estimate the demand for2009 at t = 10
Sales forecast for 2010
T x = 10
T t = 3.41 + 022(10)
T 10 = 3.41 + 2.2
T 10 = 5.61
Thus, the trend components yield a sales forecast of 5.61 since the units are by 1,000.
Thus, the estimated demand for 2009 is 5, 610 units of DVD.
t = 11
T 11 = 3.41 + 0.22(11)
T 11 = 3.41 + 2.42
T 11 = 5.83
Hence, the estimate sales forecast for 2010 is 5,830 units of DVD.
8
Sales 5
0
1 2 3 4 5 6 7 8 9
Period
DVD SALES
These forecasting methods are based on the assumption that the variable we are trying
to forecast exhibits a cause-effect relationship with one or more variable(s).
Regression Analysis
Formula:
a = Y-axis intercept
The dependent variable Ŷ is the item we are trying to forecast, while the independent
variable (X) is an item that might have a casual effect on the dependent variable.
∑ XY −nXY
b= ; a = Ŷ – bX
∑ X 2 −n X 2
Example:
Dumlao Construction Firm renovates homes in Marilao, Bulacan. Over time, the
business has found that its Peso volume renovation work is dependent work is dependent in the
Marilao / Bulacan area payroll. The data for Dumlao’s revenue and the amount of money earned
by wage earners in Marilao, Bulacan for the past 5 years are shown below:
Y X
Dumlao’s Sales Payroll
(₱100,000) (₱1,000,000)
3.0 2
2.0 3
3.5 2
2.0 5
3.0 4
Sales Payroll X2 XY
Y X
3.0 2 4 6.0
2.0 3 9 6.0
3.5 6 36 21.0
3.5 5 25 17.5
3.0 4 16 12.0
∑Y = 15 ∑X = 20 ∑X2 ∑XY = 62.5
∑ X 20
X= = =4
5 5
∑ Y 15
Y= = =3
5 5
∑ XY −nXY 62.5−5( 4)(3) 2.5
b= = = = 0.25
∑ X 2 −n X 2 90−5 (4)2 10
a = Y = bX = 3 – 0.25(4) = 2
Ŷ =2 + 0.25X
or
Sales = 2 + 0.25(Payroll)
If Dumlao Construction wishes to have a payroll of five point five million (₱5.5M) next
year, an estimated sales for Dumlao Construction is:
= 2 + 0.25(5.5)
= 2 + 1.375
= 3.375
NAME: __________________________________________DATE:_________________
SECTION/TIME/DAY:_________________________ROOM:_____________RATING________
Exercise 15
Period 1 2 3 4 5 6 7
Observation 24 34 36 37 41 44 45
a. Compute for:
i. Naïve Method
b. Plot the original time series and comment on the appropriateness of a linear trend.
2. Suppose that the University of the West had the following data of its growth of enrollment
from 2016-2014.
Year Enrollment
2006 3000
2007 3200
2008 3600
2009 3650
2010 4000
2011 4200
2012 4300
2013 4410
2014 4520
a. Forecast the 2015 enrollment using three-year weighted moving average forecast.
3. For the Philippines Basketball Association (PBA) 2013-2014 season, San Mig James Yap
was the scoring leader with an average of 33 points per game. The following data shows the
average of points per game for the scoring leader from the 2008-2009 season to the 2013-2014
season.
Season Average
2008-2009 25
2009-2010 35
2010-2011 29
2011-2012 34
2012-2013 35
2013-2014 33
a. Use exponential smoothing to forecast this time series. Consider smoothing constant of ɑ =
0.20 and ɑ = 0.30. What value of the smoothing constant provides the best forecast/
b. What is the forecast of the leading scoring average for the 2014-2015 season?
Use initial value for F 1 = 200 and identify which value of ɑ is the best.
1 2 3 4 5 6 7 8 9 10 11 12
35M 27M 37M 41M 45M 38M 44M 42M 39M 43M 39M 40M
Month Complaints
January 60
February 48
March 55
April 50
May 55
a. Compute a three-month weighted moving average.
b. Prepare forecast for June, July and August.
8. Given: Gasoline Sales (time series) of PETRON (weekly)
a. Compute the three-week and four-week moving average for the time series.
b. Compute the MAD for three-week and four-week moving average forecasts.
c. What appears to be the best number of weeks of past data to be used in the moving
average computation?
d. Compute the percentage error and MAPE.
9. Use the exponential smoothing with ɑ = 0.40 and an initial value of F 1 = 50 for the following
time series.
Month Demand
January 60
February 70
March 55
April 60
May 45
June 60
July 65
Compute the following:
a. Percentage error
b. MAPE
c. Absolute accuracy percentage
d. Arithmetic accuracy
10. The JAVILL Department Store has been an authorized dealer for flat TV for the past five
years. The numbers of flat TV sold each year is shown in the table.
2 25
3 35
4 39
5 43
Branches 1 2 3 4 5 6
Sales (1,000) 12 15 16 18 14 17
Profits (1,000) 7 9 10 12 10 13
Forecasting
CASE STUDY
The poor economy of 2009 resulted in the verging permanent closure of Manila Zoo. The
administration of the City of Manila decided to hire the RC Animal Park Corporation to operate
the Manila Zoo.
The RC Animal Park Corporation realized that it is a must to maintain the image of the Zoo
as a good place for visitors to relax and spend time together with their families. to accomplish
their goal, they have to assure that the place is clean. The corporation also added more
animals, birds, and reptiles to attract more visitors. They also introduced new activities and
games. The efforts of the Corporation seem to be working because the attendance increased
from 70,000 in 2009 to an all-time high of 165,000 in 2013 as shown in the following table.
Discussion Questions
1. Based on the data above, can you forecast the attendance for 2015 to 2020?
2. What forecasting technique will be most suitable to forecast the attendance from 2015 to
2020? Why?
MS EXCEL APPLICATIONS
IN FORECASTING
Example 1.
Given below are the unemployment rates and corresponding sales experienced by the Vi-An
Merchandise in the past 10 years. For numbers 1 to 4, forecast the unemployment rate next year using
the techniques indicated below and for Number 6, forecast the sales for the next three years.
Sales
Year Time Rate (%) (₱) 1. Naïve Mehod
2000 1 7.2 20,000 2.Six Years moving average
2001 2 4 41,000 3. Three years moving average with weights 1,4,3
2002 3 7.3 17,000 4. Simple exponential smoothing, ꚙ = 40%
5. Linear trend forecast unemployement rate (apply for the
2003 4 5.5 35,000 next three years)
6. Forecast the sales for the next three years using the liner
regression based on the forecasted unemployment rates in
2004 5 6.8 35,000 number 5.
7. Draw the two scatter diagrams with trend line and
2005 6 6 31,000 regression line.
2006 7 5.4 38,000
2007 8 3.6 50,000
2008 9 8.4 15,000
2009 10 7 19,000
In the spreadsheet, encode the time (periods) in column B, the rate (%) in column C and the sales (P)
in column F. Construct the table for F, in column D and error or ( F t – Rate) in column E, which will be
used in forecasting the inflation rate by simple exponential smoothing method. The following Excel
formula is used to suggest calculations of the forecast rate:
1. Naïve method, D15 F t = C13 7%, since the last column entry of actual inflation rates is in
C13.
2. Six periods moving average, D16 Ft = average (C8:C13) 6.2% where the highlighted C8 to
C13 are the entries of the six most recent inflation rates.
3. Moving average with weights 1, 4, 3 assigned to the inflation rates in the three most recent
periods, in cell D17 type =, type (1* click C11, the 3 rd most recent period + 4* click C12, the 2nd
most recent period + 3* click C13, the most recent period, then type), then type /(Divided by) 8
Ft = (1*C11 + 4*C12 + 7.275% where the denominator 8 is the sum of the weights. (See Pictures
1, 2, 3).
Picture 1
Picture 2
4. For simple exponential smoothing method, we complete the columns D and E by the following steps:
D4 and E4 are empty since there is no basis of forecasting the first period’s available actual data
a. D5 Ft = C4 since the basis of forecasting is the first period’s available actual rate in cell C4.
b. E5 Error = C5 – D5 from the 2 nd period’s available actual rate in C5 minus the corresponding
forecast value in D5.
c. Drag down this entry from cell references E5 to E13 to complete the column entries.
d. D6 Ft = D5 + 0.4*E5 from the previous forecast rate in D5 plus alpha, 40% times the previous
error in forecasting in cell E5.
e. Drag down this entry from cell references D6 to D14 to complete the column entries. The entry
in cell D14 6.62% represents the forecast value in year 2010 (See picture 2).
5. For linear trend projection, we can obtain the equation of the trend line by computing the slope and
y-intercept with the following Excel formula,
D20 is slope, b = SLOPE (C4:C13, B4:B13) where the inflation rate, R, is the array Y from C4 to C13
and the time is the array X from cells B4 to B13.
Picture 1
Picture 2
For linear regression method, first, we obtain the equation of the regression line by calculating the
slope and y-intercept using the Excel formulas SLOPE (array y, array x) and INTERCEPT (array y, array x)
where the sales in column F are the array Y and the rates in column C are the array X as shown in
Pictures 5 and 6. Hence, the linear regression equation is Sales = ₱74,127.67 - ₱7,194.06 (Rate) and the
sales for the next three years based on the forecasted inflation rates in cells E27 to E29 are the
following:
₱27,025.21
Picture 5
Picture 6
6. a. Scatter diagram for time vs. unemployment rate with trend line
To do: Highlight the arrays for Time and Rate. Click Chart Wizard. Select Scatter graph.
Right click any of the plotted points. Select Add Trend Line + Linear.
Rate (Y-axis)
9
8.4
8
7 7.2 7.3 7
6.8
6
5.5 5.4
5
4 4
3.6
3
2
1
0
0 2 4 6 8 10 12
Year (X-axis)
b. Scatter diagram for unemployment rate vs. sales with regression line
To do: Highlight the arrays for Rate and Sales. Click Chart Wizard. Select scatter graph. Right click any of
the plotted points. Select Add Trend Line + Linear.
(Sales)
60,000
50,000
40,000
30,000
20,000
10,000
0
0.05 1.05 2.05 3.05 4.05 5.05 6.05 7.05 8.05 9.05
(Unemployment Rates)
Forecasting
CASE STUDY
The poor economy of 2009 resulted in the verging permanent closure of Manila Zoo. The
administration of the City of Manila decided to hire the RC Animal Park Corporation to operate the
Manila Zoo.
The RC Animal Park Corporation realized that it is a must to maintain the image of the Zoo as a
good place for visitors to relax and spend time together with their families. To accomplish their goal,
they have to assure that the place is clean. The Corporation also added more animals, birds, and reptiles
to attract more visitors. They also introduced new activities and games. The efforts of the Corporation
seems to be working because the attendance increased from 70,000 in 2009 to an all-time high of
165,000 in 2013 as shown in the following table:
Table 5.1
Year Attendance
2014 157,800
2013 165,00
2012 120,250
2011 87,600
2010 75,800
2009 70,000
Discussion Questions
1. Based on the data above, can you forecast the attendance for 2015 to 2020?
2. What forecasting technique will be most suitable to forecast the attendance from 2015 to 2020?
Why?