Business Analysis- Time-Series Models -Measuring Forecast Error
Transcript of Business Analysis- Time-Series Models -Measuring Forecast Error
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
1/36
Slides 13b:Time-Series Models;
Measuring Forecast Error
MGS3100 Chapter 13Forecasting
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
2/36
Forecasting ModelsForecastingTechniques
QualitativeModels
Time SeriesMethods
CausalMethods
Delphi
Method
Jury ofExecutiveOpinion
Sales ForceComposite
Consumer MarketSurvey
Naive
MovingAverage
WeightedMoving Average
ExponentialSmoothing
Trend Analysis
SeasonalityAnalysisSimple
RegressionAnalysis
MultipleRegressionAnalysis
MultiplicativeDecomposition
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
3/36
Time Series Models General Form: Y = T * C * S , where
T = Trend - long term movement of mean C = (Business) Cycle - an upturn or downturn not
caused by seasonal variation; effect of theeconomy S = Seasonal Variation - repetitive pattern
observed over a specific time period = Error (random variation)
Practical Forecast Form: = T * S C is important, but difficult to forecast
Dont forecast an error!
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
4/36
A stationary time series
Linear trend time series
Linear trend and seasonality time series
Time
Time
series
value
Future
Components of a Time Series
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
5/36
Time Series: Stationary Models Stationary Model Assumptions
Assumes item forecasted will stay steady over time (constantmean; random variation only)
Techniques will smooth out short-term irregularities Forecast for period t+1 is equal to forecast for period t+k; the
forecast is revised only when new data becomes available.
Stationary Model Types Nave Forecast Moving Average Weighted Moving Average Exponential Smoothing
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
6/36
Stationary Time Series Models:
The Nave Model Whatever happened
last period willhappen again this
time The model is simple
and flexible Provides a baseline
to measure othermodels
Attempts to captureseasonal factors atthe expense of
ignoring trend
dataMonthly:
dataQuarterly:
12
4
!
!
tt
tt
YF
YF
1! tt YFor
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
7/36
Measures of Forecast Error
Bias - The arithmetic sum of theerrors
MAD - Mean Absolute Deviation MAPE Mean Absolute Percentage
Error
Mean Square Error (MSE) - Similarto simple sample variance
Standard Error - Standard deviation ofthe sampling distribution (the squareroot of the MSE)
Bias, MAD, and MAPE - typically
used for time series
)(tt
FYErrorForecast !
TFYMADtt
T
t
/||/T|errorforecast|1
T
1t
!! ! !
TYFYMAPEttt
T
t
/]/|[|1001
! !
TFY
Bias
tt
T
t
/)(
/Terror)(forecast
1
T
1t
!
!
!
!
TFY
MSE
tt
T
t
/)(
/T|errorforecast|
2
1
T
1t
2
!
!
!
!
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
8/36
Nave ForecastWallace Garden SupplyForecasting
Period
Actual
Value
Nave
Forecast Err or
Absolute
Error
Percent
Error
Squared
Error
January 10 N/A
February 12 10 2 2 16.67% 4.0
March 16 12 4 4 25.00% 16.0
April 13 16 -3 3 23.08% 9.0
May 17 13 4 4 23.53% 16.0
June 19 17 2 2 10.53% 4.0
July 15 19 -4 4 26.67% 16.0
August 20 15 5 5 25.00% 25.0
September 22 20 2 2 9.09% 4.0
October 19 22 -3 3 15.79% 9.0November 21 19 2 2 9.52% 4.0
December 19 21 -2 2 10.53% 4.0
0.818 3 17.76% 10.091
BIAS MAD MAPE MSE
Standard Error (Square Root of MSE) = 3.176619
Storage Shed Sales
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
9/36
Nave Forecast GraphWallace Garden - Naive Fore cast
0
5
10
15
20
25
February March April May June July August September October November December
Period
S
h
ed
s Actual Value
Nave Forecast
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
10/36
The Moving Average Method
The forecast is the average of the last nobservations of the time series.
n
YYYF
ntttt
111
...
!
Stationary Time Series Models:
Moving Averages
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
11/36
Moving AveragesWallace Garden SupplyForecasting
Period ActualValue Three-Month Moving AveragesJanuary 10February 12March 16April 13 10 + 12 + 16 / 3 = 12.67May 17 12 + 16 + 13 / 3 = 13.67June 19 16 + 13 + 17 / 3 = 15.33July 15 13 + 17 + 19 / 3 = 16.33August 20 17 + 19 + 15 / 3 = 17.00September 22 19 + 15 + 20 / 3 = 18.00October 19 15 + 20 + 22 / 3 = 19.00November 21 20 + 22 + 19 / 3 = 20.33December 19 22 + 19 + 21 / 3 = 20.67
Storage Shed Sales
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
12/36
Moving Averages ForecastWallace Garden SupplyForecasting 3 period moving average
Input Data Forecast ErrorAnalysis
Period Actual Value Forecast Err or
Absolute
error
Squared
error
Absolute
% errorMonth 1 10
Month 2 12
Month 3 16
Month 4 13 12.667 0.333 0.333 0.111 2.56%
Month 5 17 13.667 3.333 3.333 11.111 19.61%
Month 6 19 15.333 3.667 3.667 13.444 19.30%
Month 7 15 16.333 -1.333 1.333 1.778 8.89%
Month 8 20 17.000 3.000 3.000 9.000 15.00%
Month 9 22 18.000 4.000 4.000 16.000 18.18%
Month 10 19 19.000 0.000 0.000 0.000 0.00%
Month 11 21 20.333 0.667 0.667 0.444 3.17%
Month 12 19 20.667 -1.667 1.667 2.778 8.77%
Average 1.333 2.000 6.074 10.61%
Next period 19.667 BIAS MAD MSE MAPE
Actual Value - Forecast
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
13/36
Moving Averages GraphThree Period Moving Average
0
5
10
15
20
25
1 2 3 4 5 6 7 8 9 10 11 12
Time
Valu
e Actual Value
Forecast
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
14/36
Stability vs. Responsiveness
Should I use a 2-period moving average or a3-period moving average?
The larger the n the more stable the forecast.A 2-period model will be more responsive tochange.
We dont want to chase outliers.
But we dont want to take forever to correct fora real change.
We must balance stability with responsiveness.
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
15/36
The Weighted Moving Average MethodHistorical values of the time series are assigneddifferent weights when performing the forecast
Stationary Time Series Models:Weighted Moving Averages
1tF
= w1Yt + w2Yt-1 +w3Yt-2 + + wnYt-n+17wi = 1
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
16/36
Weighted Moving AverageWallace Garden SupplyForecasting
Period
Actual
Value Weights Three-Month Weighted Moving Averages
January 10 0.222
February 12 0.593March 16 0.185
April 13 2.2+ 7.1 + 3 / 1 = 12.298
May 17 2.7 + 9.5 + 2.4 / 1 = 14.556
June 19 3.5 + 7.7 + 3.2 / 1 = 14.407
July 15 2.9 + 10 + 3.5 / 1 = 16.484
August 20 3.8+ 11 + 2.8 / 1 = 17.814
September 22 4.2 + 8.9 + 3.7 / 1 = 16.815
October 19 3.3 + 12 + 4.1 / 1 = 19.262November 21 4.4 + 13 + 3.5 / 1 = 21.000
December 19 4.9 + 11 + 3.9 / 1 = 20.036
Next period 20.185
Sum of weights = 1.000
Storage Shed Sales
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
17/36
Weighted Moving AverageWallace Garden Supply Forecasting 3 period weighted moving averageInput Data Forecast ErrorAnalysis
Period Actual value Weights Forecast Err or
Absolute
error
Squared
error
Absolute
% error
Month 1 10 0.222Month 2 12 0.593
Month 3 16 0.185
Month 4 13 12.298 0.702 0.702 0.492 5.40%
Month 5 17 14.556 2.444 2.444 5.971 14.37%
Month 6 19 14.407 4.593 4.593 21.093 24.17%
Month 7 15 16.484 -1.484 1.484 2.202 9.89%
Month 8 20 17.814 2.186 2.186 4.776 10.93%
Month 9 22 16.815 5.185 5.185 26.889 23.57%Month 10 19 19.262 -0.262 0.262 0.069 1.38%
Month 11 21 21.000 0.000 0.000 0.000 0.00%
Month 12 19 20.036 -1.036 1.036 1.074 5.45%
Average 1.988 6.952 6.952 10.57%
Next period 20.185 BIAS MAD MSE MAPE
Sum of weights = 1.000
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
18/36
Stationary Time Series Models:
Exponential SmoothingExponential Smoothing
Moving average technique that requires a minimumamount of past data
Uses a smoothing constant with a value between 0 and 1(Usual range 0.1 to 0.3)
Forecast for period t = Forecast for period t-1 plus timesthe difference between the actual value and forecast in
period t-1: t = t-1 + (Yt-1 - t-1), or Can also be expressed as: t = (Yt-1) + (1- )(t-1) =
(Actual value in period t-1) + (1- )(Forecast in period t-1)
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
19/36
Exponential Smoothing Data
PeriodActual
Value(Yt) t-1 Yt-1 t-1 t
January 10 = 10 0.1February 12 10 + 0.1 *( 10 - 10 ) = 10.000March 16 10 + 0.1 *( 12 - 10 ) = 10.200
April 13 10.2 + 0.1 *( 16 - 10.2 ) = 10.780May 17 10.78 + 0.1 *( 13 - 10.78 ) = 11.002June 19 11.002 + 0.1 *( 17 - 11.002 ) = 11.602July 15 11.602 + 0.1 *( 19 - 11.602 ) = 12.342
August 20 12.342 + 0.1 *( 15 - 12.342 ) = 12.607September 22 12.607 + 0.1 *( 20 - 12.607 ) = 13.347October 19 13.347 + 0.1 *( 22 - 13.347 ) = 14.212November 21 14.212 + 0.1 *( 19 - 14.212 ) = 14.691December 19 14.691 + 0.1 *( 21 - 14.691 ) = 15.322
Storage Shed Sales
Class Exercise: What is the forecast for January of the following year?How about March? Find the Bias, Mad & MAPE. (Note: equals 0.1.)
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
20/36
Exponential Smoothing(Alpha = .419)
Wallace Garden SupplyForecasting Exponential smoothing
Input Data Forecast ErrorAnalysis
Period Actual value Forecast Err or
Absolute
error
Squared
error
Absolute
% error
Month 1 10 10.000Month 2 12 10.000 2.000 2.000 4.000 16.67%
Month 3 16 10.838 5.162 5.162 26.649 32.26%
Month 4 13 13.000 0.000 0.000 0.000 0.00%
Month 5 17 13.000 4.000 4.000 16.000 23.53%
Month 6 19 14.675 4.325 4.325 18.702 22.76%
Month 7 15 16.487 -1.487 1.487 2.211 9.91%
Month 8 20 15.864 4.136 4.136 17.106 20.68%
Month 9 22 17.596 4.404 4.404 19.391 20.02%
Month 10 19 19.441 -0.441 0.441 0.194 2.32%
Month 11 21 19.256 1.744 1.744 3.041 8.30%
Month 12 19 19.987 -0.987 0.987 0.973 5.19%
Average 2.608 9.842 14.70%
Alpha 0.419 MAD MSE MAPE
Next period 19.573
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
21/36
Exponential SmoothingExponential Smoothing
0
5
10
15
20
25
Janu
ary
February Ma
rch April May June JulyAu
gust
Sept
ember
October
Nove
mber
December
Sheds Actual value
Forecast
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
22/36
Evaluating the Performanceof Forecasting Techniques
Several forecasting methods have been
presented.
Which one of these forecasting methods
gives the best forecast?
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
23/36
Time 1 2 3 4 5 6Time series: 100 110 90 80 105 115
3-Period Moving average: 100 93.33 91.6
Error for the 3-Period MA: - 20 11.67 23.43-Period Weighted MA(.5, .3, .2) 98 89 85.5
Error for the 3-Period WMA - 18 16 29.5
Performance Measures
Sample Example Find the forecasts and the errors for each forecasting
technique applied to the following stationary time series.
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
24/36
MAD forthe moving averagetechnique:
MAD forthe weighted moving averagetechnique:
= 21.17
= 18.35|-20| + |11.67| + |23.4|
3MAD = =
7 `(t|n
|-18| + |116| + |29.5|
3MAD = =
7 `(t|n
Performance Measures
MAD for the Sample Example
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
25/36
MAPE forthe moving averagetechnique:
MAPE forthe weighted moving averagetechnique:
= .211
= .188|-20|/80 + |11.67|/105+ |23.4|/115
3MAPE= =
7 `(t|n
|-18|/80 + |16|/105 + |29.5|/115
3MAPE= =
7 `(t|n
Performance Measures
MAPE for the Sample Example
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
26/36
Use the performance measures to select a good setof values for each model parameter.
For the moving average: the number of periods (n).For the weighted moving average:
The number of periods (n), The weights (wi).
For the exponential smoothing: The exponential smoothing factor (E).
Excel Solver can be used to determine the valuesof the model parameters.
Performance Measures
Selecting Model Parameters
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
27/36
Trend & Seasonality
Trend analysisTechnique that fits a trend equation (or curve) to aseries of historical data pointsProjects the equation into the future for medium andlong term forecasts. Typically do not want to forecast
into the future more than half the number of timeperiods used to generate the forecast
Seasonality analysisAdjustment to time series data due to variations at
certain periods.Adjust with seasonal index - ratio of average value ofthe item in a season to the overall annual average value.Examples: demand for coal in winter months; demandfor soft drinks in the summer and over major holidays
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
28/36
Linear Trend Analysis
Midwestern Manufacturing Sales
ScatterDiagram
Actual
value (or)Y
Period
number(or) X
74 1995
79 1996
80 1997
90 1998
105 1999
142 2000
122 2001
Sales(in units) vs. Time
0
20
40
60
80
100
120
140
160
1994 1995 1996 1997 1998 1999 2000 2001 2002
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
29/36
Least Squares forLinear Regression
Midwestern ManufacturingLeast Squares Method
Time
Valueso
fDependentVariab
les
Objective: Minimizethe squared deviations!
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
30/36
Least Squares Method
bXaY
^
!
Where
Y^
= predicted value of the dependent variable (demand)
a = Y-axis intercept = - b*
b = Slope of the regression line =]Xn-XY[__
Y
-
_22 Xn-X
X = value of the independent variable (time)
XY
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
31/36
Linear Trend Data & Error Analysis
Midwestern Manufacturing CompanyForecasting Linear trend analysis
Input Data Forecast ErrorAnalysis
Period
Actual value
(or) Y
Period number
(or) X Forecast Err or
Absolute
error
Squared
error
Absolute
% error
Year 1 74 1 67.250 6.750 6.750 45.563 9.12%
Year 2 79 2 77.786 1.214 1.214 1.474 1.54%
Year 3 80 3 88.321 -8.321 8.321 69.246 10.40%
Year 4 90 4 98.857 -8.857 8.857 78.449 9.84%
Year 5 105 5 109.393 -4.393 4.393 19.297 4.18%
Year 6 142 6 119.929 22.071 22.071 487.148 15.54%
Year 7 122 7 130.464 -8.464 8.464 71.644 6.94%Average 8.582 110.403 8.22%
Intercept 56.714 MAD MSE MAPE
Slope 10.536
Next period 141.000 8
Enter the actual values in cells shaded YELLOW. Enter new time period at the bottom toforecast
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
32/36
Least Squares GraphTrend Analysis
y = 10.536x + 56.714
0
20
40
60
80
100
120
140
160
1 2 3 4 5 6 7
Time
Value
Actual values Linear (Actual values)
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
33/36
Run linear regression to testF1 in the modelYt=F0+F1t+It
Excel results:Coeff. Stand. Err t-Stat P-value Lower 95 Upper 95Intercept 369.27 27.79436 13.2857 5E-18 313.44 425.094
Weeks 0.3339 0.912641 0.36586 0.71601 -1.49919 2.166990.71601
This large P-value indicates
that there is little evidence that trend exists
Conclusion: A stationary model is appropriate.
Another way to Determine Trend:
Use the Excel Regression Function
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
34/36
Forecasting Seasonal Data: Quick Method
Eichler Supplies
Year Month Demand
Average
Demand Ratio
Seasonal
Index
1 January 80 94 0.851 0.957
February 75 94 0.798 0.851
March 80 94 0.851 0.904
April 90 94 0.957 1.064
May 115 94 1.223 1.309
June 110 94 1.170 1.223
July 100 94 1.064 1.117 August 90 94 0.957 1.064
September 85 94 0.904 0.957
October 75 94 0.798 0.851
November 75 94 0.798 0.851
December 80 94 0.851 0.851
2 January 100 94 1.064 0.957
February 85 94 0.904 0.851
March 90 94 0.957 0.904
April 110 94 1.170 1.064May 131 94 1.394 1.309
June 120 94 1.277 1.223
July 110 94 1.170 1.117
August 110 94 1.170 1.064
September 95 94 1.011 0.957
October 85 94 0.904 0.851
November 85 94 0.904 0.851
December 80 94 0.851 0.851
Seasonal Index ratioof theaverage value of the item in aseason to the overall averageannual value.
Example: average ofyear 1January ratio to year 2 Januaryratio.(0.851 + 1.064)/2 = 0.957
Ratio = Demand / Average Demand
IfYear 3 average monthly demand isexpected to be 100 units.Forecast demand Year 3 January:
100 X 0.957 = 96 unitsForecast demand Year 3 May:
100 X 1.309 = 131 units
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
35/36
Forecasting Seasonal Data With Trend
1. Calculate the seasonal indices (as shown on theprevious slide)
2. Calculate deseasonalized treand by dividingthe actual value (Y) by the seasonal index forthat period:Deseasonalized Trend = Y / Seasonal index
(e.g., 80 units/ 0.957 = 83.595)
3. Find the trend line, and extend the trend line intothe desired forecast period.
-
8/3/2019 Business Analysis- Time-Series Models -Measuring Forecast Error
36/36
Forecasting Seasonal Data With Trend:
Calculating the Seasonal Forecast4. Now that we have the Seasonal Indices and Trend
line, we can reseasonalize the data and generatethe seasonalized forecast by multiplying thetrend line values in the forecast period by theappropriate seasonal indices for each time period
as follows: = Trend x Seasonal Index