Forecasting. Forecast… is a statement about the future value of a variable of interest (such as...
-
Upload
diane-black -
Category
Documents
-
view
214 -
download
0
Transcript of Forecasting. Forecast… is a statement about the future value of a variable of interest (such as...
Forecasting
Forecast…
• is a statement about the future value of a variable of interest (such as demand).
• affects decisions and activities throughout an organization.
• reduces uncertainty (replaces data).
General statements about forecasting
• Assumes causal systempast ==> future
• Forecasts rarely perfect because of randomness (Be ready to react).
• Forecasts more accurate forgroups vs. individuals
• Forecast accuracy decreases as time horizon increases
Possible targets of forecasting
• Factors outside the organization, that are hard to change – eg. weather, inflation, unemployment
• Factors within the organization with a greater possibility to change.– eg. age structure, labor turnover, scrap ratio
The good forecasting system…
+ cost effectiveness
Timely
AccurateReliable
Mea
ningfu
l
Written
Easy
to u
se
Steps in the forecasting process
Step 1 Determine purpose of forecast
Step 2 Establish a time horizon
Step 3 Select a forecasting technique
Step 4 Gather and analyze data
Step 5 Prepare the forecast
Step 6 Monitor the forecast
“The forecast”
Forecast accuracy (measures of goodness)
Forecast error: et = At – Ft
Mean absolute deviation: MADn
FAMAD
n
ttt
1
Mean squared error: MSE
Mean absoulute percent error: MAPE
1
)(1
2
n
FAMSE
n
ttt
n
A
FA
MAD
n
t t
tt100
1
MAPE
Period Actual Forecast (A-F) |A-F| (A-F)^2 (|A-F|/Actual)*1001 217 215 2 2 4 0.922 213 216 -3 3 9 1.413 216 215 1 1 1 0.464 210 214 -4 4 16 1.905 213 211 2 2 4 0.946 219 214 5 5 25 2.287 216 217 -1 1 1 0.468 212 216 -4 4 16 1.89
-2 22 76 10.26
MAD= 2.75MSE= 10.86
MAPE= 1.28
Types of forecast
• Judgmental - uses subjective inputs
– Executive opinions, salesforce opinions, consumer surveys etc.
• Time series (time ordered sequence of observations) - uses historical data assuming the future will be like the past
• Associative models - uses explanatory variables to predict the future
Time series forecasts
• Trend - long-term movement in data• Seasonality - short-term regular variations in data• Cycle – wavelike variations of more than one year’s
duration• Irregular variations - caused by unusual circumstances• Random variations - caused by chance
Forecast Variations
Trend
Irregularvariation
Seasonal variations
908988
Cycles
Naive forecasts
• The forecast for any period equals the previous period’s actual value.
• Advantages:– Simple to use– Virtually no cost– Quick and easy to prepare– Data analysis is nonexistent– Easily understandable– Cannot provide high accuracy– Can be a standard for accuracy
3 uses of naive forecasts
• Stable time series data– F(t) = A(t-1)
• Seasonal variations– F(t) = A(t-n)
• Data with trends– F(t) = A(t-1) + (A(t-1) – A(t-2))
Techniques of averaging(smoothing variations in the data)
• (Simple) Avarage
• Moving average
• Weighted moving average
• Exponential smoothing
Average
Time
Variable
Moving average
Ft = (At-n+…+At-2+At-1)/n
Example (3 yrs):1. € 42
2. € 40
3. € 43
4. € 40
5. € 41
6. €?
New data:
6. € 38
7. ?
New data:
7. € 37
8. ?
What would be the forecast with 5 years moving average?
0
1
2
3
4
5
6
0 1 2 3 4 5 6
If the trend is permanent
Mottó: egy biztos – minden bizonytalan
Az előrejelzés a jövőbeni események megjósolásának tudománya és művészete
Miért tudomány?
Miért művészet?0
1
2
3
4
5
6
0 1 2 3 4 5 6
Changing trend
Weighted moving average
• Előrejelzés2.104
5
625
321
11031002951
• Súlyok:
• Data: Aug. 95
Sept. 100
Oct. 110
Nov. ?
Time Present -1 -2
Weight 3 2 1
Forecast:
Weights:
Exponential smoothing
New forecast = forecast for the previous period + α*error
Where the error is = actual data for the last period – forecasted data for the last
period
α: smoothing constant (usually 0.05<α<0.5)
)F - (A F 1-t1-t1-t tF
Linear trends
Ft = a + btwhere
And where n = number of periods, y = value of the time series
Nonlinear trends
Associative Forecasting
• Predictor variables - used to predict values of variable interest
• Regression - technique for fitting a line to a set of points
• Least squares line - minimizes sum of squared deviations around the line
Controlling the Forecast
• Control chart– A visual tool for monitoring forecast errors– Used to detect non-randomness in errors
• Forecasting errors are in control if– All errors are within the control limits– No patterns, such as trends or cycles, are
present
Sources of Forecast errors
• Model may be inadequate
• Irregular variations
• Incorrect use of forecasting technique
Choosing a Forecasting Technique
• No single technique works in every situation
• Two most important factors– Cost– Accuracy
• Other factors include the availability of:– Historical data– Computers– Time needed to gather and analyze the data– Forecast horizon