Upload
bibhutinanda
View
228
Download
0
Embed Size (px)
Citation preview
8/12/2019 8721 Forecasting 2013
1/35
Forecasting for Operations Decisions
W S William
8/12/2019 8721 Forecasting 2013
2/35
Forecasting is the art and science of predictingfuture events.
Institute of Business Forecasting
8/12/2019 8721 Forecasting 2013
3/35
3-3
Elements of a Good Forecast
Timely
AccurateReliable
Written
8/12/2019 8721 Forecasting 2013
4/35
Key Issues in Forecasting
Choice of forecasting horizon (a week, a month etc.)
A forecasting method with desired accuracy.
The unit of forecasting ( gross sales, individual product
demand etc.)
8/12/2019 8721 Forecasting 2013
5/35
Forecast Horizon
Forecast horizon is the period for which forecast is prepared
Long-Range (years)
( e.g. Process selection, Capacity addition)
Medium-Range (months)
(e.g. Manpower planning, procurement of long lead time items)
Short-Range (weeks)
(e.g. Production schedules, overtimes etc.)
8/12/2019 8721 Forecasting 2013
6/35
Examples of Production Resource Forecasts
ForecastHorizon
Time Span Item Being Forecast Units ofMeasure
Long-Range Years
Product lines
Factory capacities
Planning for new products
Capital expenditures
Facility location or expansionR&D
Dollars, tons, etc.
Medium-
RangeMonths
Product groups
Department capacities
Sales planning
Production planning and budgeting
Dollars, tons, etc.
Short-Range Weeks
Specific product quantitiesMachine capacities
Planning
Purchasing
Scheduling
Workforce levels
Production levels
Job assignments
Physical units of
products
8/12/2019 8721 Forecasting 2013
7/35
8/12/2019 8721 Forecasting 2013
8/35
Forecasting Methods
Broadly, forecasting methods fall under two categories:
Qualitative Methods : These are subjective in nature (ExecutiveOpinion, Market Research , Delphi Method)
Quantitative Methods: They use mathematical or simulationmethods base d on historical demand or relationshipsbetween variables.
Extrapolated or Time Series(Use past data to forecast future)
Explanatory or Causal Method (Establishes a relationshipbetween dependent and independent variables); y= f(x)
8/12/2019 8721 Forecasting 2013
9/35
Components of Demand
Horizontal Component
Trend Component
Seasonal Component
8/12/2019 8721 Forecasting 2013
10/35
Simple Moving Average
An averaging period (AP) is given or selected
The forecast for the next period is the
arithmetic average of the AP most recent
actual demands It is called a simple average because each
period used to compute the average is equally
weighted
. . . more
8/12/2019 8721 Forecasting 2013
11/35
Simple Moving Average
It is called moving because as new demand
data becomes available, the oldest data is notused
By increasing the AP, the forecast is lessresponsive to fluctuations in demand (lowimpulse response)
By decreasing the AP, the forecast is moreresponsive to fluctuations in demand (highimpulse response)
8/12/2019 8721 Forecasting 2013
12/35
Simple Moving Average
Week Demand
1 650
2 678
3 7204 785
5 859
6 920
7 850
8 7589 892
10 920
11 789
12 844
F = A + A + A +...+An
tt -1 t-2 t-3 t-n
Lets develop 3-week and6-week moving average
forecasts for demand.
Assume you only have 3weeks and 6 weeks of
actual demand data for the
respective forecasts
8/12/2019 8721 Forecasting 2013
13/35
Week Demand 3-Week 6-Week
1 650
2 678
3 720
4 785 682.67
5 859 727.67
6 920 788.00
7 850 854.67 768.67
8 758 876.33 802.009 892 842.67 815.33
10 920 833.33 844.00
11 789 856.67 866.50
12 844 867.00 854.83
Simple Moving Average
Slide 13 of 55
8/12/2019 8721 Forecasting 2013
14/35
Simple Moving Average
Slide 14 of 55
8/12/2019 8721 Forecasting 2013
15/35
8/12/2019 8721 Forecasting 2013
16/35
Weighted Moving Average
The weights must add to 1.0 and generally
decrease in value with the age of the data
The distribution of the weights determine
impulse response of the forecast
8/12/2019 8721 Forecasting 2013
17/35
Weighted Moving Average
F = w A + w A + w A +...+w At 1 t -1 2 t -2 3 t-3 n t - n
w = 1ii=1
n
Determine the 3-period
weighted moving average
forecast for period 4
Weights (adding up to 1.0):
t-1: .5
t-2: .3
t-3: .2
Week Demand
1 650
2 678
3 720
4
8/12/2019 8721 Forecasting 2013
18/35
Moving Average Method
Step1:Select the number of periods for which movingaverage will be computed, thus number N is called an order of
moving average
Step 2:Take the average demand for the most recent N
periods. This average demand then becomes the forecast for
the next period.
8/12/2019 8721 Forecasting 2013
19/35
3-19
Exponential Smoothing
Premise--The most recent observationsmight have the highest predictive value.
Therefore, we should give more weight to the
more recent time periods when forecasting.
Ft= Ft-1 + (At-1 - Ft-1)
8/12/2019 8721 Forecasting 2013
20/35
8/12/2019 8721 Forecasting 2013
21/35
Simple Linear Regression
Relationship between one independent variable, X, and a
dependent variable, Y.
Assumed to be linear (a straight line)
Form: Y = a + bX
Y = dependent variable
X = independent variable
a = y-axis intercept
b = slope of regression line
8/12/2019 8721 Forecasting 2013
22/35
Simple Linear Regression Model
b is similar to the slope. However, since it
is calculated with the variability of the datain mind, its formulation is not as straight-
forward as our usual notion of slope
Yt= a + bx
0 1 2 3 4 5 x (weeks)
Y
8/12/2019 8721 Forecasting 2013
23/35
Calculating a and b
a = y - bx
b = xy - n(y)(x)
x -n(x2 2
)
8/12/2019 8721 Forecasting 2013
24/35
Regression Equation Example
Week Sales
1 150
2 1573 162
4 166
5 177
Develop a regression equation to predict sales
based on these five points.
8/12/2019 8721 Forecasting 2013
25/35
Week Week*Week Sales Week*Sales
1 1 150 150
2 4 157 314
3 9 162 486
4 16 166 6645 25 177 885
3 55 162.4 2499
Average Sum Average Sum
b =xy - n(y)(x)
x - n(x=
2499 - 5(162.4)(3)=
a = y - bx = 162.4 - (6.3)(3) =
2 2
) ( )55 5 9
63
10 6.3
143.5
Regression Equation Example
Slide 25 of 55
8/12/2019 8721 Forecasting 2013
26/35
y = 143.5 + 6.3t
135
140
145
150
155
160
165
170
175
180
1 2 3 4 5Period
Sales
Sales
Forecast
Regression Equation Example
Slide 26 of 55
8/12/2019 8721 Forecasting 2013
27/35
Forecast Accuracy
Accuracy is the typical criterion for judging the
performance of a forecasting approach
Accuracy is how well the forecasted values
match the actual values
8/12/2019 8721 Forecasting 2013
28/35
Monitoring Accuracy
Accuracy of a forecasting approach needs to be
monitored to assess the confidence you can have in
its forecasts and changes in the market may require
reevaluation of the approach
Accuracy can be measured in several ways
Mean absolute deviation (MAD)
Mean squared error (MSE)
8/12/2019 8721 Forecasting 2013
29/35
Mean Squared Error (MSE)
MSE = (Syx)2
Small value for Syxmeans data points tightlygrouped around the line and error range issmall. The smaller the standard error the
more accurate the forecast.
MSE = 1.25(MAD)
When the forecast errors are normally
distributed
8/12/2019 8721 Forecasting 2013
30/35
8/12/2019 8721 Forecasting 2013
31/35
Solution
MAD =
A - F
n=
40
4= 10
t tt=1
n
Month Sales Forecast Abs Error
1 220 n/a
2 250 255 5
3 210 205 5
4 300 320 20
5 325 315 10
40
8/12/2019 8721 Forecasting 2013
32/35
3-32
Tracking Signal
Tracking signal = (Actual -forecast)MAD
Tracking signalRatio of cumulative error to MAD
BiasPersistent tendency for forecasts to be
Greater or less than actual values.
8/12/2019 8721 Forecasting 2013
33/35
Criteria for Selecting a Forecasting Method
Cost
Accuracy
Data available
Time span
Nature of products and services
Impulse response and noise dampening
8/12/2019 8721 Forecasting 2013
34/35
Reasons for Ineffective Forecasting
Not involving a broad cross section of people
Not recognizing that forecasting is integral to business
planning
Not recognizing that forecasts will always be wrong (think in
terms of interval rather than point forecasts)
Not forecasting the right things
(forecast independent demand only)
Not selecting an appropriate forecasting method
(use MAD to evaluate goodness of fit)
Not tracking the accuracy of the forecasting models
8/12/2019 8721 Forecasting 2013
35/35
Thank you