Adeyl Khan, Faculty, BBA, NSU Chapter 5, 6, 7. Adeyl Khan, Faculty, BBA, NSU.
Adeyl Khan, Faculty, BBA, NSU Car buyer- Models & Option Does the dealer know! Basic Managerial...
-
Upload
janel-weaver -
Category
Documents
-
view
216 -
download
0
Transcript of Adeyl Khan, Faculty, BBA, NSU Car buyer- Models & Option Does the dealer know! Basic Managerial...
Adeyl Khan, Faculty, BBA, NSU
Chapter 3 Forecasting
Car buyer- Models & OptionDoes the dealer know!
Basic Managerial function- Planning
Adeyl Khan, Faculty, BBA, NSU
Forecast
A statement about the future value of a variable of interest such as demand.Forecasting is used to make informed decisions.
Long-range (Plan system) Short-range (Plan use of system)
3-2
TrafficWeather
I see that you willget an A this semester.
Adeyl Khan, Faculty, BBA, NSU
Uses of Forecasts
3-3
Accounting Cost/profit estimates
Finance Cash flow and funding
Human Resources Hiring/recruiting/training
Marketing Pricing, promotion, strategy
MIS IT/IS systems, services
Operations Schedules, MRP, workloads
Product/service design New products and services
Example!
Adeyl Khan, Faculty, BBA, NSU
Features of Forecasts
• Assumes causal system. past ==> future
• Forecasts rarely perfect because of randomness
• Forecasts more accurate for groups vs. individuals
• Forecast accuracy decreases as time horizon increases
3-4
Timely Reliable
Accurate
Meaningful
Written Easy to use
Elements of a Good Forecast
Adeyl Khan, Faculty, BBA, NSU
Steps in the Forecasting ProcessStep 1
Determine purpose of
forecast
Step 2 Establish a
time horizon
Step 3 Select a forecasting
technique
Step 4 Obtain, clean and
analyze data
Step 5 Make the forecast
Step 6 Monitor the
forecast
TrafficWeathe
r
Adeyl Khan, Faculty, BBA, NSU
Types of ForecastJudgmentalTime seriesAssociative models
3-6
QuantitativeQualitative
Adeyl Khan, Faculty, BBA, NSU
1. Judgmental ForecastsExecutive opinionsSales force opinionsConsumer surveysOutside opinionDelphi method
Opinions of managers and staff (Experts) Anonymous, encourage honesty,
Questionnaire sequence Achieves a consensus forecast
Other usage of this method
3-7
Subjective/Qualitative inputs
Adeyl Khan, Faculty, BBA, NSU
2. Time Series ForecastsUses historical dataTrend - long-term movement in dataSeasonality - short-term regular variations
in data Specific dates, days, times
Cycle – wavelike variations of more than one year’s duration Economic, political, GDP …
3-8
Irregular variations - caused by unusual circumstances
• Atypical- remove from analysis
Random variations - caused by chance
• Include?
Adeyl Khan, Faculty, BBA, NSU
Forecast Variations
3-9
Trend
Irregularvariation
Seasonal variations
908988
Figure 3.1
Cycles
Adeyl Khan, Faculty, BBA, NSU
2. Time Series Forecasts Naive Forecasts
3-10
Uh, give me a minute.... We sold 250 wheels last week.... Now, next week we should sell....
The forecast for any period equals the previous period’s actual value.
Adeyl Khan, Faculty, BBA, NSU
Naïve Forecasts
Simple to useVirtually no costQuick and easy to prepareData analysis is nonexistentEasily understandableCannot provide high accuracyCan be a standard for accuracy
3-11
Adeyl Khan, Faculty, BBA, NSU
Uses for Naïve Forecasts
Stable time series data F(t) = A(t-1) | Forecast(Feb) = Actual (Feb -1=Jan)
Seasonal variations F(t) = A(t-n) | Forecast(July) = Actual (July -4=Mar)
Data with trends F(t) = A(t-1) + (A(t-1) – A(t-2))
3-12
Adeyl Khan, Faculty, BBA, NSU
Techniques for Averaging
Moving averageWeighted moving averageExponential smoothing
3-13
Adeyl Khan, Faculty, BBA, NSU
2. Time Series Forecasts Moving AveragesMoving average – A technique that
averages a number of recent actual values, updated as new values become available.
Weighted moving average – More recent values in a series are given more weight in computing the forecast.
3-14
Ft = MAn= nAt-n + … At-2 + At-1
Ft = WMAn= n
wnAt-n + … wn-1At-2 + w1At-1
Adeyl Khan, Faculty, BBA, NSU
Simple Moving Average
3-15
35
40
45
50
1 2 3 4 5 6 7 8 9 10 11 12
Actual
MA3
MA5
Ft = MAn= n
At-n + … At-2 + At-1
Adeyl Khan, Faculty, BBA, NSU
Ft = MAn= n
At-n + … At-2 + At-1
Ft = MA3= 3
At-3 + At-2 + At-1
Ft = MA5= 5
At-5 + At-4 + At-3 + At-2 + At-1
Adeyl Khan, Faculty, BBA, NSU
Exponential Smoothing
Premise--The most recent observations might have the highest predictive value. Therefore, we should give more weight to the more recent time periods when forecasting.
Weighted averaging method based on previous forecast plus a percentage of the forecast errorA-F is the error term, α is the % feedback
3-17
Ft = Ft-1 + (At-1 - Ft-1)
Adeyl Khan, Faculty, BBA, NSU
Example 3 - Exponential Smoothing
3-18
Period Actual Alpha = 0.1 Error Alpha = 0.4 Error1 422 40 42 -2.00 42 -23 43 41.8 1.20 41.2 1.84 40 41.92 -1.92 41.92 -1.925 41 41.73 -0.73 41.15 -0.156 39 41.66 -2.66 41.09 -2.097 46 41.39 4.61 40.25 5.758 44 41.85 2.15 42.55 1.459 45 42.07 2.93 43.13 1.87
Ft = Ft-1 + (At-1 - Ft-1)
Adeyl Khan, Faculty, BBA, NSU
Picking a Smoothing Constant
3-19
.1.4
Actual
Adeyl Khan, Faculty, BBA, NSU
Time series forecastingCommon Nonlinear Trends
3-20
Parabolic
Exponential
Growth
Figure 3.5
Adeyl Khan, Faculty, BBA, NSU
Linear Trend Equation
Ft = Forecast for period tt = Specified number of time periodsa = Value of Ft at t = 0b = Slope of the line
3-21
Ft = a + bt
0 1 2 3 4 5 t
Ft
Adeyl Khan, Faculty, BBA, NSU22
Adeyl Khan, Faculty, BBA, NSU
Calculating a and b
3-23
b = n (ty) - t y
n t2 - ( t)2
a = y - b t
n
Adeyl Khan, Faculty, BBA, NSU
Linear Trend Equation Example
3-24
tWeek
t2 ySales
ty
1 1 150 1502 4 157 3143 9 162 4864 16 166 6645 25 177 885
S t = 15 S t2 = 55 S y = 812 S ty = 2499(S t)2 =
225
Adeyl Khan, Faculty, BBA, NSU
Linear Trend Calculation
3-25
y = 143.5 + 6.3t
a = 812 - 6.3(15)
5 =
b = 5 (2499) - 15(812)
5(55) - 225 =
12495-12180
275 -225 = 6.3
143.5
Adeyl Khan, Faculty, BBA, NSU
Techniques for Seasonality
Seasonal variations Regularly repeating movements in series values that can be tied to recurring events.
Seasonal relative Percentage of average or trend
Centered moving average A moving average positioned at the center of the data that were used to compute it.
3-26
Adeyl Khan, Faculty, BBA, NSU
Types of Forecasts3. Associative ForecastingPredictor variables - used to predict values
of variable interestRegression - technique for fitting a line to a
set of pointsLeast squares line - minimizes sum of
squared deviations around the line
3-27
Adeyl Khan, Faculty, BBA, NSU
Linear Model Seems Reasonable
3-28
A straight line is fitted to a set of sample points.
0
10
20
30
40
50
0 5 10 15 20 25
X Y7 152 106 134 15
14 2515 2716 2412 2014 2720 4415 347 17
Computedrelationship
Adeyl Khan, Faculty, BBA, NSU
Linear Regression Assumptions
Variations around the line are randomDeviations around the line normally distributedPredictions are being made only within the range of observed valuesFor best results:
Always plot the data to verify linearity Check for data being time-dependent Small correlation may imply that other variables are important
3-29
Adeyl Khan, Faculty, BBA, NSU
Forecast AccuracyError - difference between
actual value and predicted value
Mean Absolute Deviation (MAD) Average absolute error
Mean Squared Error (MSE) Average of squared error
Mean Absolute Percent Error (MAPE) Average absolute percent
error3-30
MAD
• Easy to compute• Weights errors linearly
MSE
• Squares error• More weight to large errors
MAPE
• Puts errors in perspective
Adeyl Khan, Faculty, BBA, NSU
MAD, MSE, and MAPE
3-31
MAD = | Actual – forecast |
n
MSE = (Actual – forecast ) 2
n - 1
MAPE = n
( | Actual – forecast | / Actual )*100
Adeyl Khan, Faculty, BBA, NSU
Example 10
3-32
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
Adeyl Khan, Faculty, BBA, NSU
Controlling the ForecastControl 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 3-33
Sources of Forecast errors
• Model may be inadequate
• Irregular variations
• Incorrect use of forecasting technique
Adeyl Khan, Faculty, BBA, NSU
Tracking SignalRatio of cumulative error to MAD
Bias – Persistent tendency for forecasts to be Greater or less than actual values.
3-34
Tracking signal =å(Actual - forecast)
MAD
Adeyl Khan, Faculty, BBA, NSU
Choosing a Forecasting Technique
No single technique works in every situationTwo most important factors
Cost Accuracy
Other factors include the availability of: Historical data Computers Time needed to gather and analyze the data Forecast horizon
3-35
Adeyl Khan, Faculty, BBA, NSU
Operations Strategy
Forecasts are the basis for many decisionsWork to improve short-term forecastsAccurate short-term forecasts improve
Profits Lower inventory levels Reduce inventory shortages Improve customer service levels Enhance forecasting credibility
3-36
Adeyl Khan, Faculty, BBA, NSU
Supply Chain Forecasts
Sharing forecasts with supply can Improve forecast quality in the supply chain Lower costs Shorter lead times
3-37
Adeyl Khan, Faculty, BBA, NSU38
Adeyl Khan, Faculty, BBA, NSU
Learning Objectives
List the elements of a good forecast. Outline the steps in the forecasting process. Describe at least three qualitative forecasting techniques and the advantages and disadvantages of each. Compare and contrast qualitative and quantitative approaches to forecasting.
3-39
Adeyl Khan, Faculty, BBA, NSU
Learning Objectives
Briefly describe averaging techniques, trend and seasonal techniques, and regression analysis, and solve typical problems. Describe two measures of forecast accuracy. Describe two ways of evaluating and controlling forecasts. Identify the major factors to consider when choosing a forecasting technique.
3-40
Adeyl Khan, Faculty, BBA, NSU3-41
Exponential Smoothing
Adeyl Khan, Faculty, BBA, NSU3-42
Linear Trend Equation
Adeyl Khan, Faculty, BBA, NSU3-43
Simple Linear Regression