Forecasting
To accompany Quantitative Analysis for Management, Tenth Edition, by Render, Stair, and Hanna Power Point slides created by Jeff Heyl
Introduction
Managers are always trying to reduce
uncertainty and make better estimates of what will happen in the future This is the main purpose of forecasting Some firms use subjective methods Seatofthe pants methods, intuition, experience There are also several quantitative techniques Moving averages, exponential smoothing, trend projections, least squares regression analysis
52
Introduction
Forecasting is a method for translating past
experience into estimates of the future Virtually used by most management decisions such as: Working capital needs Size of workforce Inventory levels Scheduling of production runs
53
Introduction
Judgmental Forecasting is used when situations in
It is especially used when: There are a few data for building a quantitative
model Historical data are no longer representative due to drastic environmental changes Decision to be taken is critical If the forecaster views himself as an expert in the area
2009 PrenticeHall, Inc. 54
Introduction
Judgmental Forecasting Evaluated: Trends in the data caused by seasonal patterns
may be overlooked
55
Introduction
Eight steps to forecasting : 1. Determine the use of the forecastwhat 2. 3. 4. 5. 6. 7. 8.
objective are we trying to obtain? Select the items or quantities that are to be forecasted Determine the time horizon of the forecast Select the forecasting model or models Gather the data needed to make the forecast Validate the forecasting model Make the forecast Implement the results
2009 PrenticeHall, Inc. 56
Introduction
These steps are a systematic way of initiating,
designing, and implementing a forecasting system When used regularly over time, data is collected routinely and calculations performed automatically There is seldom one superior forecasting system Different organizations may use different techniques Whatever tool works best for a firm is the one they should use
2009 PrenticeHall, Inc. 57
Forecasting Models
Forecasting Techniques Qualitative Models Delphi Methods Jury of Executive Opinion Sales Force Composite Consumer Market Survey TimeSeries Methods Causal Methods Regression Analysis
Multiple Regression
TimeSeries Models
Timeseries models attempt to predict
59
Causal Models
Causal models use variables or factors
that might influence the quantity being forecasted The objective is to build a model with the best statistical relationship between the variable being forecast and the independent variables Regression analysis is the most common technique used in causal modeling
2009 PrenticeHall, Inc. 5 10
Qualitative Models
Qualitative models incorporate judgmental
or subjective factors Useful when subjective factors are thought to be important or when accurate quantitative data is difficult to obtain Common qualitative techniques are
Delphi method Jury of executive opinion Sales force composite Consumer market surveys
5 11
Qualitative Models
Delphi Method an iterative group process where
(possibly geographically dispersed) respondents provide input to decision makers Jury of Executive Opinion collects opinions of a small group of highlevel managers, possibly using statistical models for analysis Sales Force Composite individual salespersons estimate the sales in their region and the data is compiled at a district or national level Consumer Market Survey input is solicited from customers or potential customers regarding their purchasing plans
2009 PrenticeHall, Inc. 5 12
time series follows some pattern called the forecast profiles The 4 kinds of trends are: Constant Level
 assumes no trend at all in the data
Damped Trend  the amount of trend declines in each period and dies out to form a horizontal line
2009 PrenticeHall, Inc. 5 13
Timeseries Patterns
The 3 kinds of seasonalities: 1. Nonseasonal Pattern
 assumed to have a relatively constant mean
1. Additive Seasonal Pattern  assumes that the seasonal fluctuations are of constant size 1. Multiplicative Seasonal Pattern  assumes that the seasonal fluctuations are proportional to the data
5 14
Scatter Diagrams
Scatter diagrams are helpful when forecasting timeseries data because they depict the relationship between variables.
450 400 350 300 250 200 150 100 50 0 0 2 4
Radios
Annual Sales
Televisions
s pact Disc Com
6 Time (Years) 8 10 12
5 15
Scatter Diagrams
Wacker Distributors wants to forecast sales for three
different products
250 250 250 250 250 250 250 250 250 250
YEAR 1 2 3 4 5 6 7 8 9 10
Table 5.1
TELEVISION SETS
RADIOS 300 310 320 330 340 350 360 370 380 390
COMPACT DISC PLAYERS 110 100 120 140 170 150 160 190 200 190
2009 PrenticeHall, Inc. 5 16
Scatter Diagrams
(a)
Annual Sales of Televisions 330 250 200 150 100 50
         
Sales appear to be
constant over time Sales = 250 A good estimate of sales in year 11 is 250 televisions
0 1 2 3 4 5 6 7 8 9 10
Time (Years)
Figure 5.2
2009 PrenticeHall, Inc. 5 17
Scatter Diagrams
(b)
Annual Sales of Radios 420 400 380 360 340 320 300 280
         
Sales appear to be
0 1 2 3 4 5 6 7 8 9 10
increasing at a constant rate of 10 radios per year Sales = 290 + 10(Year) A reasonable estimate of sales in year 11 is 400 televisions
Time (Years)
Figure 5.2
2009 PrenticeHall, Inc. 5 18
Scatter Diagrams
This trend line may
(c)
Annual Sales of CD Players 200 180 160 140 120 100

      
not be perfectly accurate because of variation from year to year Sales appear to be increasing A forecast would probably be a larger figure each year
0 1 2 3 4 5 6 7 8 9 10
Time (Years)
Figure 5.2
2009 PrenticeHall, Inc. 5 19
to see how well one model works or to compare models Forecast error = Actual value Forecast value
5 20
Table 5.2
5 21
Table 5.2
5 22
forecast tends to be too high or too low and by how much. Thus, it can be negative or positive.
2009 PrenticeHall, Inc. 5 23
160 17.8
2009 PrenticeHall, Inc. 5 24
error/actual 0.03 0.02 0.04 0.02 0.04 0.08 0.03 0.02 0.02 0.07 0.04 0.04
spaced events (weekly, monthly, quarterly, etc.) Timeseries forecasts predict the future based solely of the past values of the variable Other variables, no matter how potentially valuable, are ignored
5 27
Decomposition of a TimeSeries
A time series typically has four components 1. Trend (T) is the gradual upward or 2.
3. 4.
downward movement of the data over time Seasonality (S) is a pattern of demand fluctuations above or below trend line that repeats at regular intervals Cycles (C) are patterns in annual data that occur every several years Random variations (R) are blips in the data caused by chance and unusual situations
5 28
Decomposition of a TimeSeries
Demand for Product or Service Trend Component Seasonal Peaks Actual Demand Line Average Demand over 4 Years
Year 2
Time
Year 3
Year 4
5 29
Decomposition of a TimeSeries
There are two general forms of timeseries
Demand = T x S x C x R
The additive model
Demand = T + S + C + R
Models may be combinations of these two forms Forecasters often assume errors are normally
5 30
Moving Averages
Moving averages can be used when demand is
relatively steady over time The next forecast is the average of the most recent n data values from the time series The most recent period of data is added and the oldest is dropped
This methods tends to smooth out shortterm
Moving Averages
Mathematically
Ft +1 = where
Yt + Yt 1 + ... + Yt n+1 n
Ft +1 = forecast for time period t + 1 Y = actualt value in time period t n = number of periods to average
5 32
demand for its Storage Shed They have collected data for the past year They are using a threemonth moving average to forecast demand (n = 3)
5 33
(10 + 12 + 13)/3 = 11.67 (12 + 13 + 16)/3 = 13.67 (13 + 16 + 19)/3 = 16.00 (16 + 19 + 23)/3 = 19.33 (19 + 23 + 26)/3 = 22.67 (23 + 26 + 30)/3 = 26.33 (26 + 30 + 28)/3 = 28.00 (30 + 28 + 18)/3 = 25.33 (28 + 18 + 16)/3 = 20.67 (18 + 16 + 14)/3 = 16.00
emphasis on recent periods Often used when a trend or other pattern is emerging
Ft +1
Mathematically
effective in smoothing out fluctuations in the demand pattern in order to provide stable estimates Problems
Increasing the size of n smoothes out
fluctuations better, but makes the method less sensitive to real changes in the data Moving averages can not pick up trends very well they will always stay within past levels and not predict a change to a higher or lower level
2009 PrenticeHall, Inc. 5 36
moving average model to forecast demand for its Storage Shed They decide on the following weighting scheme
WEIGHTS APPLIED 3 2 PERIOD Last month
1 Three months ago 3 x Sales last month + 2 x Sales two months ago + 1 X Sales three months ago Sum of the weights
2009 PrenticeHall, Inc. 5 37
[(3 X 13) + (2 X 12) + (10)]/6 = 12.17 [(3 X 16) + (2 X 13) + (12)]/6 = 14.33 [(3 X 19) + (2 X 16) + (13)]/6 = 17.00 [(3 X 23) + (2 X 19) + (16)]/6 = 20.50 [(3 X 26) + (2 X 23) + (19)]/6 = 23.83 [(3 X 30) + (2 X 26) + (23)]/6 = 27.50 [(3 X 28) + (2 X 30) + (26)]/6 = 28.33 [(3 X 18) + (2 X 28) + (30)]/6 = 23.33 [(3 X 16) + (2 X 18) + (28)]/6 = 18.67 [(3 X 14) + (2 X 16) + (18)]/6 = 15.33
Program 5.1A
2009 PrenticeHall, Inc. 5 39
Program 5.1B
2009 PrenticeHall, Inc. 5 40
Exponential Smoothing
Exponential smoothing is easy to use and
recast = Last periods forecast + (Last periods actual demand Last periods forecast) Where is a weight (or smoothing constant) with constant a value between 0 and 1 inclusive A larger gives more importance to recent data while a smaller value gives more importance to past data 2009 PrenticeHall, Inc.
5 41
Exponential Smoothing
Mathematically
Ft +1 = Ft + (Yt Ft )
Ft+1 = new forecast (for time period t + 1) Ft = pervious forecast (for time period t) = smoothing constant (0 1) Yt = pervious periods actual demand
ere
car model was predicted to be 142 Actual February demand was 153 autos Using a smoothing constant of = 0.20, what is the forecast for March?
New forecast (for March demand) = 142 + 0.2(153 142) = 144.2 or 144 autos
obtaining a good forecast The objective is always to generate an accurate forecast The general approach is to develop trial forecasts with different values of and select the that results in the lowest MAD
is key to
5 44
1 2 3 4 5 6 7 8 9 Table 5.5
5 45
1 2 3 4 5 6 7 8 Table 5.6
Best choice
deviations =
178.22
MAD =
Program 5.2A
2009 PrenticeHall, Inc. 5 47
Program 5.2B
2009 PrenticeHall, Inc. 5 48
The owners purchase generic computer parts in volume at a discount from a variety of sources whenever they see a good deal.
It is important that they develop a good forecast of
demand for their computers so they can purchase component parts efficiently.
5 49
PM Computers: Data
Period Month Actual Demand 1 Jan 37 2 Feb 40 3 Mar 41 4 Apr 37 5 May 45 6 June 50 7 July 43 8 Aug 47 9 Sept 56 Compute a 2month moving average Compute a 3month weighted average using weights of
4,2,1 for the past three months of data Compute an exponential smoothing forecast using = 0.7, previous forecast of 40 Using MAD, what forecast is most accurate? 2009 PrenticeHall, Inc. 5 50
MAD
smoothing does not respond to trends A more complex model can be used that adjusts for trends The basic approach is to develop an exponential smoothing forecast then adjust it for the trend New forecast (Ft) + Trend correction (Tt)
5 52
Tt +1 = (1 )Tt + ( Ft +1 Ft )
where Tt+1 = smoothed trend for period t + 1 Tt = smoothed trend for preceding period = trend smooth constant that we select Ft+1 = simple exponential smoothed forecast for period t + 1 Ft = forecast for pervious period
2009 PrenticeHall, Inc. 5 53
makes the forecast more responsive to changes in trend A low value of gives less weight to the recent trend and tends to smooth out the trend Values are generally selected using a trialanderror approach based on the value of the MAD for different values of Simple exponential smoothing is often referred to as firstorder smoothing Trendadjusted smoothing is called secondorder, secondorder double smoothing, or Holts method smoothing
2009 PrenticeHall, Inc. 5 54
Trend Projection
Trend projection fits a trend line to a series
of historical data points The line is projected into the future for medium to longrange forecasts Several trend equations can be developed based on exponential or quadratic models The simplest is a linear model developed using regression analysis
5 55
Trend Projection
Trend projections are used to forecast timeseries
which the independent variable (X) is the time period Least squares may be used to determine a trend projection for future forecasts.
Least squares determines the trend line forecast by
minimizing the mean squared error between the trend line forecasts and the actual observed values.
5 56
Trend Projection
The mathematical form is
Y = b0 + b1 X
where b0 b1 X = predicted value Y = intercept = slope of the line = time period (i.e., X = 1, 2, 3, , n)
5 57
Trend Projection
Dist7
*
Dist1
Dist5 Dist3
Dist6
Dist2
Dist4
Time
Figure 5.4
2009 PrenticeHall, Inc. 5 58
the following demand for its electrical generators over the period of 2001 2007
YEAR 2001 2002 2003 2004 2005 2006 2007 ELECTRICAL GENERATORS SOLD 74 79 80 90 105 142 122
Table 5.7
5 59
Program 5.3A
2009 PrenticeHall, Inc. 5 60
r2 says model predicts about 80% of the variability in demand Significance level for Ftest indicates a definite relationship
Program 5.3B
2009 PrenticeHall, Inc. 5 61
Y = 56.71 + 10.54 X
To project demand for 2008, we use the coding
system to define X = 8
Actual Demand Line Trend Line Y = 56.71 + 10.54 X
Figure 5.5
2001 2002 2003 2004 2005 2006 2007 2008 2009 Year
2009 PrenticeHall, Inc. 5 63
Program 5.4A
2009 PrenticeHall, Inc. 5 64
Program 5.4B
2009 PrenticeHall, Inc. 5 65
Seasonal Variations
Recurring variations over time may
indicate the need for seasonal adjustments in the trend line A seasonal index indicates how a particular season compares with an average season When no trend is present, the seasonal index can be found by dividing the average value for a particular season by the average of all the data
5 66
Seasonal Variations
Eichler Supplies sells telephone
answering machines Data has been collected for the past two years sales of one particular model They want to create a forecast that includes seasonality
5 67
Seasonal Variations
MONTH SALES DEMAND YEAR 1 YEAR 2 AVERAGE TWOYEAR DEMAND MONTHLY DEMAND AVERAGE SEASONAL INDEX 0.957 0.851 0.904 1.064 1.309 1.223 1.117
94 94 94 94 94 94 94
Table 5.8
Seasonal Variations
The calculations for the seasonal indices are
Jan. Feb. Mar. Apr. May June
1,200 0.957 = 96 12 1,200 0.851 = 85 12 1,200 0.904 = 90 12 1,200 1.064 = 106 12 1,200 1.309 = 131 12 1,200 1.223 = 122 12
1,200 1.117 = 112 12 1,200 1.064 = 106 12 1,200 0.957 = 96 12 1,200 0.851 = 85 12 1,200 0.851 = 85 12 1,200 0.851 = 85 12
2009 PrenticeHall, Inc. 5 69
the seasons
Y = a + b1 X 1 + b2 X 2 + b3 X 3 + b4 X 4
where X1 X2 X3 X4 = time period = 1 if quarter 2, 0 otherwise = 1 if quarter 3, 0 otherwise = 1 if quarter 4, 0 otherwise
2009 PrenticeHall, Inc. 5 70
Program 5.6A
2009 PrenticeHall, Inc. 5 71
Y = 104 .1 + 2.3(13 ) + 15.7(0) + 38.7(0) + 30.1(0) = 134 Y = 104 .1 + 2.3(14 ) + 15.7(1) + 38.7(0) + 30.1(0) = 152
These are different from the results obtained using the
multiplicative decomposition method Use MAD and MSE to determine the best model
5 73
system used only timeseries methods to forecast the demand for spare parts
This method was slow to responds to even moderate
which uses linear regression to establish a relationship between monthly part removals and various functions of monthly flying hours
The computation now takes only one hour instead of
the days the old system needed Using RAPS provided a one time savings of $7 million and a recurring annual savings of nearly $1 million
2009 PrenticeHall, Inc. 5 74
performance of a forecast Tacking signals are computed using the following equation
RSFE Tracking signal = MAD where
Time
Figure 5.7
2009 PrenticeHall, Inc. 5 76
than forecast Negative tracking signals indicate demand is less than forecast Some variation is expected, but a good forecast will have about as much positive error as negative error Problems are indicated when the signal trips either the upper or lower predetermined limits This indicates there has been an unacceptable amount of variation Limits should be reasonable and may vary from item to item
2009 PrenticeHall, Inc. 5 77
high volume stock items and 8 MADs for lower volume items
One MAD is equivalent to approximately 0.8
are expected to fall within 2 MADs, 98% with 3 MADs or 99.9% within 4 MADs whenever the errors are approximately normally distributed
2009 PrenticeHall, Inc.
5 78
1 2 3 4 5 6
10 15 0 10 +5 +35
10 5 15 10 15 30
10 15 30 40 55 85
1 2 0 1 +0.5 +2.5
Forecasting at Disney
The Disney chairman receives a daily
report from his main theme parks that contains only two numbers the forecast of yesterdays attendance at the parks and the actual attendance
An error close to zero (using MAPE as the
measure) is expected
5 80
mediumsized forecasting problems More advanced programs (SAS, SPSS, Minitab) handle timeseries and causal models May automatically select best model parameters Dedicated forecasting packages may be fully automatic May be integrated with inventory planning and control
2009 PrenticeHall, Inc. 5 81
Much more than documents.
Discover everything Scribd has to offer, including books and audiobooks from major publishers.
Cancel anytime.