Forecasting Techniques Qualitative Models Delphi Methods Jury of Executive Opinion Sales Force Composite Consumer Market Survey

Time-Series Methods

Causal Methods
Regression Analysis

Moving Average Exponential Smoothing Trend Projections Decomposition

Multiple Regression

 Time-series

models attempt to predict the future based on the past Common time-series models are

Moving average Exponential smoothing Trend projections Decomposition

Regression

analysis is used in trend projections and one type of decomposition model

 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

 Wacker Distributors wants to forecast sales

for three different products

TELEVISION SETS
250 250 250 250 250 250 250 250 250 250

YEAR
1 2 3 4 5 6 7 8 9 10

RADIOS
300 310 320 330 340 350 360 370 380 390

COMPACT DISC PLAYERS

110 100 120 140 170 150 160 190 200 190

(a)
Annual Sales of Televisions 330

Sales appear to be

250
200 150 100 50
| | | | | | | | | |

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)

(b)

420 400 Annual Sales of Radios

Sales appear to be

380
360 340 320

300 280
|

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)

 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)

We compare forecasted values with actual values to see how well one model works or to compare models

Forecast error = Actual value Forecast value

One measure of accuracy is the mean absolute deviation (MAD) forecast error MAD n

Using a nave forecasting model

ACTUAL SALES OF CD PLAYERS 110 100 120 140 170 150 160 190 200 FORECAST SALES 110 100 120 140 170 150 160 190 ABSOLUTE VALUE OF ERRORS (DEVIATION), (ACTUAL FORECAST) |100 110| = 10 |120 110| = 20 |140 120| = 20 |170 140| = 30 |150 170| = 20 |160 150| = 10 |190 160| = 30 |200 190| = 10

YEAR 1 2 3 4 5 6 7 8 9

10
11

190

200
190

|190 200| = 10
Sum of |errors| = 160 MAD = 160/9 = 17.8

Using a nave forecasting model

YEAR 1 2 3 4 5 6 7 8 9 ACTUAL SALES OF CD PLAYERS 110 100 120 140 170 150 160 190 200 FORECAST SALES 110 100 120 140 170 150 160 190 ABSOLUTE VALUE OF ERRORS (DEVIATION), (ACTUAL FORECAST) |100 110| = 10 |120 110| = 20 |140 120| = 20 |170 140| = 30 |150 170| = 20 |160 150| = 10 |190 160| = 30 |200 190| = 10

10
11

190

200
190

|190 200| = 10
Sum of |errors| = 160 MAD = 160/9 = 17.8

MAD

forecast error 160 17.8 n 9

YEAR
1` 2 3 4 5 6 7 8 9 10 11

SALES
1400 1600 1800 2000 1800 6000 5000 6000 6000 7000

FORECAST
1800 2000 3000 3000 8000 6000 7000 7000 8000 9000

DEVIATION

MAD

There are other popular measures of forecast accuracy The mean squared error

(error)2 MSE n
The mean absolute percent error

error actual MAPE 100% n

And bias is the average error

time series is a sequence of evenly spaced events Time-series forecasts predict the future based solely of the past values of the variable Other variables are ignored

A time series typically has four components 1. Trend (T) is the gradual upward or downward movement of the data over time 2. Seasonality (S) is a pattern of demand fluctuations above or below trend line that repeats at regular intervals 3. Cycles (C) are patterns in annual data that occur every several years 4. Random variations (R) are blips in the data caused by chance and unusual situations

Demand for Product or Service

Trend Component Seasonal Peaks Actual Demand Line Average Demand over 4 Years

Year 1

Year 2

Time

Year 3

Year 4

There are two general forms of time-series models The multiplicative model

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 distributed with a mean of zero

 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 This methods tends to smooth out short-term irregularities in the data series

Moving average forecast

Sum of demands in previous n periods n

 Mathematically

Ft 1

Yt Yt 1 ... Yt n1 n

where
Ft 1 = forecast for time period t + 1 Yt

= actual value in time period t n = number of periods to average

 IIPM wants to forecast demand They have collected data for the past year

They are using a three-month moving

average to forecast demand (n = 3)

MONTH January February March

ACTUAL ASMISSIONS 10 12 13

THREE-MONTH MOVING AVERAGE

April
May June July August September October November December January

16
19 23 26 30 28 18 16 14

(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

MONTH January February March April May June

SALES 200 220 230 200 180 230

THREE-MONTH MOVING AVERAGE

July
August September October November December January

260
300 280 180 160 140

 Weighted moving averages use weights to put more

emphasis on recent periods Often used when a trend or other pattern is emerging
Ft 1

( Weight in period i )( Actual value in period) ( Weights)

w1Yt w2Yt 1 ... wnYt n1 Ft 1 w1 w2 ... wn
wi = weight for the ith observation

Mathematically

where

 IIPM decides to try a weighted moving

average model to forecast demand They decide on the following weighting scheme
WEIGHTS APPLIED 3 2 1 6 Sum of the weights PERIOD Last month Two months ago Three months ago

3 x Sales last month + 2 x Sales two months ago + 1 X Sales three months ago

MONTH January February March April

ACTUAL SHED SALES 10 12 13 16

THREE-MONTH WEIGHTED MOVING AVERAGE

[(3 X 13) + (2 X 12) + (10)]/6 = 12.17 [(3 X 16) + (2 X 13) + (12)]/6 = 14.33

May
June July August September

19
23 26 30 28

[(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

October
November December January

18
16 14

MONTH January February March April

SALES 100 120 130 160

THREE-MONTH WEIGHTED MOVING AVERAGE

May
June July August September October November December January

190
230 260 300 280 180 160 140

Exponential smoothing is easy to use and requires little record keeping of data It is a type of moving average

New forecast = Last periods forecast + (Last periods actual demand - Last periods forecast)

Where is a weight (or smoothing constant) with a value between 0 and 1 inclusive

Mathematically

Ft 1 Ft (Yt Ft )
where

Ft+1 = new forecast (for time period t + 1) Ft = previous forecast (for time period t) = smoothing constant (0 1) Yt = pervious periods actual demand

The idea is simple the new estimate is

the old estimate plus some fraction of the error in the last period

In January, Februarys demand for a certain 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

If actual demand in March was 136 autos,

the April forecast would be

New forecast (for April demand)

= 144.2 + 0.2(136 144.2) = 142.6 or 143 autos

 Selecting the appropriate value for

to 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

 Exponential smoothing forecast for two values of

ACTUAL TONNAGE UNLOADED 180 168 159 175 190 205 180 175 175.5 = 175.00 + 0.10(180 175) 174.75 = 175.50 + 0.10(168 175.50) 173.18 = 174.75 + 0.10(159 174.75) 173.36 = 173.18 + 0.10(175 173.18) 175.02 = 173.36 + 0.10(190 173.36) 178.02 = 175.02 + 0.10(205 175.02) FORECAST USING =0.10

QUARTER
1 2 3 4 5 6 7

FORECAST USING =0.50 175 177.5 172.75 165.88 170.44 180.22 192.61

8
9

182
?

178.22 = 178.02 + 0.10(180 178.02)

178.60 = 178.22 + 0.10(182 178.22)

186.30
184.15

QUARTER
1 2 3 4 5 6 7 8

ACTUAL TONNAGE UNLOADED 180 168 159 175 190 205 180 182

FORECAST WITH = 0.10 175 175.5 174.75 173.18 173.36 175.02 178.02 178.22 |deviations| n

ABSOLUTE DEVIATIONS FOR = 0.10 5.. 7.5.. 15.75 1.82 16.64 29.98 1.98 3.78 82.45 = 10.31

FORECAST WITH = 0.50 175 177.5 172.75 165.88 170.44 180.22 192.61 186.30

ABSOLUTE DEVIATIONS FOR = 0.50 5. 9.5.. 13.75 9.12 19.56 24.78 12.61 4.3.. 98.63

Sum of absolute deviations MAD =

MAD =

12.33

Best choice

QUARTER 1 2 3 4 5

SALES 800 600 500 700 900

FORECAST USING =

FORECAST USING =

6 7
8 9

600 800
700 ?

Like all averaging techniques, exponential 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

Forecast including trend (FITt) =

New forecast (Ft) + Trend correction (Tt)

The equation for the trend correction uses a new smoothing constant Tt is computed by

Tt 1 (1 )T1 ( 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

 As with exponential smoothing, a high value of

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 trial-and-error approach based on the value of the MAD for different values of Simple exponential smoothing is often referred to as first-order smoothing Trend-adjusted smoothing is called second-order, double smoothing, or Holts method

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 long-range forecasts Several trend equations can be developed based on exponential or quadratic models The simplest is a linear model developed using regression analysis

Trend Projection
The mathematical form is

Y b0 b1 X

where

Y = predicted value

b0 = intercept b1 = slope of the line X = time period (i.e., X = 1, 2, 3, , n)

Trend Projection
Dist7

Value of Dependent Variable

*
Dist1

Dist5 Dist3

Dist6

Dist2

Dist4

Time

 Midwestern Manufacturing Company has experienced

the following demand for its electrical generators over the period of 2001 2007
YEAR ELECTRICAL GENERATORS SOLD

2001 2002 2003 2004 2005 2006 2007

74 79 80 90 105 142 122

r2 says model predicts about 80% of the variability in demand Significance level for F-test indicates a definite relationship

 The forecast equation is

Y 56.71 10.54 X
To project demand for 2008, we use the coding

system to define X = 8

(sales in 2008) = 56.71 + 10.54(8) = 141.03, or 141 generators

Likewise for X = 9

(sales in 2009) = 56.71 + 10.54(9) = 151.57, or 152 generators

160 150 140 Generator Demand 130 120 110

Actual Demand Line Trend Line Y 56.71 10.54 X

100
90 80 70 60

50
| | | | | | | | |

2001 2002 2003 2004 2005 2006 2007 2008 2009 Year

 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

 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 this includes seasonality

SALES DEMAND MONTH January February March YEAR 1 80 85 80 YEAR 2 100 75 90

AVERAGE TWOYEAR DEMAND 90 80 85

MONTHLY DEMAND 94 94 94

AVERAGE SEASONAL INDEX 0.957 0.851 0.904

April
May June July August

110
115 120 100 110

90
131 110 110 90

100
123 115 105 100

94
94 94 94 94

1.064
1.309 1.223 1.117 1.064

September
October November December

85
75 85 80

95
85 75 80 1,128 = 94 12 months

90
80 80 80

94
94 94 94

0.957
0.851 0.851 0.851

Total average demand = 1,128 Average monthly demand = Seasonal index =

Average two-year demand Average monthly demand

The calculations for the seasonal indices are

Jan.
Feb. Mar. Apr. May
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

July
Aug. Sept. Oct. Nov.

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

June

Dec.

SALES DEMAND MONTH January February March YEAR 1 800 800 800 YEAR 2 700 750 900

AVERAGE TWOYEAR DEMAND

MONTHLY DEMAND

AVERAGE SEASONAL INDEX

April
May June July August

1000
1500 1200 1000 1100

900
1300 1300 1200 800

September
October November December

800
700 950 900

950
800 750 850

Seasonal Variations with Trend

When both trend and seasonal components are present, the forecasting task is more complex Seasonal indices should be computed using a centered moving average (CMA) approach There are four steps in computing CMAs 1. Compute the CMA for each observation (where possible) 2. Compute the seasonal ratio = Observation/CMA for that observation 3. Average seasonal ratios to get seasonal indices 4. If seasonal indices do not add to the number of seasons, multiply each index by (Number of seasons)/(Sum of indices)

Turner Industries Example

The following are Turner Industries sales figures for

the past three years

YEAR 1 108 125 150 141 131.00

QUARTER 1 2 3 4 Average

YEAR 2 116 134 159 152 140.25

YEAR 3 123 142 168 165 149.50

AVERAGE 115.67 133.67 159.00 152.67 140.25

Definite trend

Seasonal pattern

Turner Industries Example

To calculate the CMA for quarter 3 of year 1 we

compare the actual sales with an average quarter centered on that time period We will use 1.5 quarters before quarter 3 and 1.5 quarters after quarter 3 that is we take quarters 2, 3, and 4 and one half of quarters 1, year 1 and quarter 1, year 2
0.5(108) + 125 + 150 + 141 + 0.5(116) CMA(q3, y1) = 4

= 132.00

Turner Industries Example

We compare the actual sales in quarter 3 to

the CMA to find the seasonal ratio

Seasonal ratio

Sales in quarter 3 150 1.136 CMA 132

Turner Industries Example

YEAR 1 QUARTER 1 2 3 4 1 2 3 4 1 2 3 4 SALES 108 125 150 141 116 134 159 152 123 142 168 165 CMA SEASONAL RATIO

132.000 134.125 136.375 138.875 141.125 143.000 145.125 147.875

1.136 1.051 0.851 0.965 1.127 1.063 0.848 0.960

Turner Industries Example

There are two seasonal ratios for each quarter so

these are averaged to get the seasonal index Index Index Index Index for for for for quarter quarter quarter quarter 1 2 3 4 = = = = I1 I2 I3 I4 = = = = (0.851 (0.965 (1.136 (1.051 + + + + 0.848)/2 0.960)/2 1.127)/2 1.063)/2

= = = =

0.85 0.96 1.13 1.06

Turner Industries Example

Scatter plot of Turner Industries data and

CMAs
200 150 Sales 100 CMA

50
0
| |

Original Sales Figures

| | | | | | | | | |

5 6 7 Time Period

10

11

12

Decomposition is the process of isolating linear trend and seasonal factors to develop more accurate forecasts There are five steps to decomposition 1. Compute seasonal indices using CMAs 2. Deseasonalize the data by dividing each number by its seasonal index 3. Find the equation of a trend line using the deseasonalized data 4. Forecast for future periods using the trend line 5. Multiply the trend line forecast by the appropriate seasonal index

Problem
YEAR 1 QUARTER 1 2 3 4 1 2 3 4 1 2 3 4 SALES 100 120 135 140 160 140 150 150 120 140 180 160 CMA SEASONAL RATIO

SALES ($1,000,000s) 108 125 150 141 116 134 159 152 123 142 168 165

SEASONAL INDEX 0.85 0.96 1.13 1.06 0.85 0.96 1.13 1.06 0.85 0.96 1.13 1.06

DESEASONALIZED SALES ($1,000,000s) 127.059 130.208 132.743 133.019 136.471 139.583 140.708 143.396 144.706 147.917 148.673 155.660

 Find a trend line using the deseasonalized data

b1 = 2.34

b0 = 124.78

Develop a forecast using this trend a multiply the

forecast by the appropriate seasonal index

Y = 124.78 + 2.34X = 124.78 + 2.34(13) = 155.2 (forecast before adjustment for seasonality) Y x I1 = 155.2 x 0.85 = 131.92

 A San Diego hospital used 66 months of adult

inpatient days to develop the following seasonal indices

SEASONALITY INDEX 1.0436 0.9669 MONTH July August SEASONALITY INDEX 1.0302 1.0405

MONTH January February

March
April May June

1.0203
1.0087 0.9935 0.9906

September
October November December

0.9653
1.0048 0.9598 0.9805

 Using this data they developed the following

equation where

Y = 8,091 + 21.5X Y = forecast patient days X = time in months

Based on this model, the forecast for patient days

for the next period (67) is

Patient days = 8,091 + (21.5)(67) = 9,532 (trend only)

Patient days = (9,532)(1.0436) = 9,948 (trend and seasonal)

Multiple regression can be used to forecast both trend and seasonal components in a time series

One independent variable is time Dummy independent variables are used to represent the seasons

The model is an additive decomposition model

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

The resulting regression equation is

Y 104.1 2.3 X 1 15.7 X 2 38.7 X 3 30.1X 4

Using the model to forecast sales for the first two

quarters of next year

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

 Tracking signals can be used to monitor the

performance of a forecast Tacking signals are computed using the following equation
RSFE Tracking signal MAD

where

forecast error MAD

n
RSFE = Ratio of running sum of forecast errors = (actual demand in period i - forecast demand in period i)

Signal Tripped + 0 MADs Upper Control Limit Tracking Signal

Acceptable Range

Lower Control Limit

Time

 Positive tracking signals indicate demand is greater

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

Adaptive smoothing is the computer monitoring of tracking signals and self-adjustment if a limit is tripped In exponential smoothing, the values of and are adjusted when the computer detects an excessive amount of variation