forecasting mba
DESCRIPTION
forecastTRANSCRIPT
4 - 1© 2011 Pearson Education, Inc. publishing as Prentice Hall
What is Forecasting?What is Forecasting?
Process of predicting a future event
Underlying basis of all business decisions Production
Inventory
Personnel
Facilities
??
4 - 2© 2011 Pearson Education, Inc. publishing as Prentice Hall
The Realities!The Realities!
Forecasts are seldom perfect
Most techniques assume an underlying stability in the system
Product family and aggregated forecasts are more accurate than individual product forecasts
4 - 3© 2011 Pearson Education, Inc. publishing as Prentice Hall
Short-range forecast Up to 1 year, generally less than 3 months
Purchasing, job scheduling, workforce levels, job assignments, production levels
Medium-range forecast 3 months to 3 years
Sales and production planning, budgeting
Long-range forecast 3+ years
New product planning, facility location, research and development
Forecasting Time HorizonsForecasting Time Horizons
4 - 4© 2011 Pearson Education, Inc. publishing as Prentice Hall
Forecasting ApproachesForecasting Approaches
Used when little data exist New products
New technology
Involves intuition, experience e.g., forecasting sales on
Internet
Qualitative MethodsQualitative Methods
4 - 5© 2011 Pearson Education, Inc. publishing as Prentice Hall
Qualitative MethodsQualitative Methods
1. Jury of executive opinion (Pool opinions of high-level experts, sometimes augment by statistical models)
2. Delphi method (Panel of experts, queried iteratively until consensus is reached)
3. Sales force composite (Estimates from individual salespersons are reviewed for reasonableness, then aggregated)
4. Consumer Market Survey (Ask the customer)
4 - 6© 2011 Pearson Education, Inc. publishing as Prentice Hall
Quantitative ApproachesQuantitative Approaches
Used when situation is ‘stable’ and historical data exist Existing products
Current technology
Involves mathematical techniques e.g., forecasting sales of LCD
televisions
4 - 7© 2011 Pearson Education, Inc. publishing as Prentice Hall
Quantitative ApproachesQuantitative Approaches
1. Naive approach
2. Moving averages
3. Exponential smoothing
4. Trend projection
5. Linear regression
time-series models
associative model
4 - 8© 2011 Pearson Education, Inc. publishing as Prentice Hall
Set of evenly spaced numerical data Obtained by observing response
variable at regular time periods
Forecast based only on past values, no other variables important Assumes that factors influencing
past and present will continue influence in future
Time Series ForecastingTime Series Forecasting
4 - 9© 2011 Pearson Education, Inc. publishing as Prentice Hall
Trend
Seasonal
Cyclical
Random
Time Series ComponentsTime Series Components
4 - 10© 2011 Pearson Education, Inc. publishing as Prentice Hall
Components of DemandComponents of DemandD
eman
d f
or
pro
du
ct o
r se
rvic
e
| | | |1 2 3 4
Time (years)
Average demand over 4 years
Trend component
Actual demand line
Random variation
Figure 4.1
Seasonal peaks
4 - 11© 2011 Pearson Education, Inc. publishing as Prentice Hall
Persistent, overall upward or downward pattern
Changes due to population, technology, age, culture, etc.
Typically several years duration
Trend ComponentTrend Component
4 - 12© 2011 Pearson Education, Inc. publishing as Prentice Hall
Regular pattern of up and down fluctuations
Due to weather, customs, etc.
Occurs within a single year
Seasonal ComponentSeasonal Component
Number ofPeriod Length Seasons
Week Day 7Month Week 4-4.5Month Day 28-31Year Quarter 4Year Month 12Year Week 52
4 - 13© 2011 Pearson Education, Inc. publishing as Prentice Hall
Repeating up and down movements
Affected by business cycle, political, and economic factors
Multiple years duration
Cyclical ComponentCyclical Component
0 5 10 15 20
4 - 14© 2011 Pearson Education, Inc. publishing as Prentice Hall
Erratic, unsystematic, ‘residual’ fluctuations
Due to random variation or unforeseen events
Short duration and nonrepeating
Random ComponentRandom Component
M T W T F
4 - 15© 2011 Pearson Education, Inc. publishing as Prentice Hall
Naive ApproachNaive Approach
Assumes demand in next period is the same as demand in most recent period e.g., If January sales were 68, then
February sales will be 68
Sometimes cost effective and efficient
Can be good starting point
4 - 16© 2011 Pearson Education, Inc. publishing as Prentice Hall
MA is a series of arithmetic means
Used if little or no trend
Used often for smoothing Provides overall impression of data
over time
Moving Average MethodMoving Average Method
Moving average =∑ demand in previous n periods
n
4 - 17© 2011 Pearson Education, Inc. publishing as Prentice Hall
Used when some trend might be present Older data usually less important
Weights based on experience and intuition
Weighted Moving AverageWeighted Moving Average
Weightedmoving average =
∑ (weight for period n) x (demand in period n)
∑ weights
4 - 18© 2011 Pearson Education, Inc. publishing as Prentice Hall
Increasing n smooths the forecast but makes it less sensitive to changes
Do not forecast trends well
Require extensive historical data
Potential Problems WithPotential Problems With Moving Average Moving Average
4 - 19© 2011 Pearson Education, Inc. publishing as Prentice Hall
Form of weighted moving average Weights decline exponentially
Most recent data weighted most
Requires smoothing constant () Ranges from 0 to 1
Subjectively chosen
Involves little record keeping of past data
Exponential SmoothingExponential Smoothing
4 - 20© 2011 Pearson Education, Inc. publishing as Prentice Hall
Exponential SmoothingExponential Smoothing
New forecast = Last period’s forecast+ (Last period’s actual demand
– Last period’s forecast)
Ft = Ft – 1 + (At – 1 - Ft – 1)
where Ft = new forecast
Ft – 1 = previous forecast
= smoothing (or weighting) constant (0 ≤ ≤ 1)
4 - 21© 2011 Pearson Education, Inc. publishing as Prentice Hall
Common Measures of ErrorCommon Measures of Error
Mean Absolute Deviation (MAD)
MAD =∑ |Actual - Forecast|
n
Mean Squared Error (MSE)
MSE =∑ (Forecast Errors)2
n
4 - 22© 2011 Pearson Education, Inc. publishing as Prentice Hall
Common Measures of ErrorCommon Measures of Error
Mean Absolute Percent Error (MAPE)
MAPE =∑100|Actuali - Forecasti|/Actuali
n
n
i = 1
4 - 23© 2011 Pearson Education, Inc. publishing as Prentice Hall
Exponential Smoothing with Exponential Smoothing with Trend AdjustmentTrend Adjustment
When a trend is present, exponential smoothing must be modified to respond to trend
Forecast including (FITt) = trend
Exponentially Exponentiallysmoothed (Ft) + smoothed (Tt)forecast trend
4 - 24© 2011 Pearson Education, Inc. publishing as Prentice Hall
Exponential Smoothing with Exponential Smoothing with Trend AdjustmentTrend Adjustment
Ft = (At - 1) + (1 - )(Ft - 1 + Tt - 1)
Tt = (Ft - Ft - 1) + (1 - )Tt - 1
Step 1: Compute Ft
Step 2: Compute Tt
Step 3: Calculate the forecast FITt = Ft + Tt
4 - 25© 2011 Pearson Education, Inc. publishing as Prentice Hall
Trend ProjectionsTrend Projections
Fitting a trend line to historical data points to project into the medium to long-range
Linear trends can be found using the least squares technique
y = a + bx^
where y= computed value of the variable to be predicted (dependent variable)a= y-axis interceptb= slope of the regression linex= the independent variable
^
4 - 26© 2011 Pearson Education, Inc. publishing as Prentice Hall
Least Squares MethodLeast Squares Method
Equations to calculate the regression variables
b =xy - nxy
x2 - nx2
y = a + bx^
a = y - bx
4 - 28© 2011 Pearson Education, Inc. publishing as Prentice Hall
Seasonal Variations In DataSeasonal Variations In Data
The multiplicative seasonal model can adjust trend data for seasonal variations in demand (jet skis, snow mobiles)
4 - 29© 2011 Pearson Education, Inc. publishing as Prentice Hall
Seasonal Variations In DataSeasonal Variations In Data
1. Find average historical demand for each season
2. Compute the average demand over all seasons
3. Compute a seasonal index for each season
4. Estimate next year’s total demand
5. Divide this estimate of total demand by the number of seasons, then multiply it by the seasonal index for that season
Steps in the process:Steps in the process:
4 - 30© 2011 Pearson Education, Inc. publishing as Prentice Hall
Associative ForecastingAssociative Forecasting
Used when changes in one or more independent variables can be used to predict
the changes in the dependent variable
Most common technique is linear regression analysis
We apply this technique just as we did We apply this technique just as we did in the time series examplein the time series example
4 - 31© 2011 Pearson Education, Inc. publishing as Prentice Hall
Associative ForecastingAssociative ForecastingForecasting an outcome based on predictor variables using the least squares technique
y = a + bx^
where y= computed value of the variable to be predicted (dependent variable)a= y-axis interceptb= slope of the regression linex= the independent variable though to predict the value of the dependent variable
^
4 - 32© 2011 Pearson Education, Inc. publishing as Prentice Hall
Standard Error of the Standard Error of the EstimateEstimate
A forecast is just a point estimate of a future value
This point is actually the mean of a probability distribution
Figure 4.9
4.0 –
3.0 –
2.0 –
1.0 –
| | | | | | |0 1 2 3 4 5 6 7
No
del
’s s
ales
Area payroll
3.25
4 - 33© 2011 Pearson Education, Inc. publishing as Prentice Hall
Standard Error of the Standard Error of the EstimateEstimate
We use the standard error to set up prediction intervals around the
point estimate
Sy,x =∑y2 - a∑y - b∑xy
n - 2
4 - 34© 2011 Pearson Education, Inc. publishing as Prentice Hall
Standard Error of the Standard Error of the EstimateEstimate
4.0 –
3.0 –
2.0 –
1.0 –
| | | | | | |0 1 2 3 4 5 6 7
No
del
’s s
ales
Area payroll
3.25
Sy,x = =∑y2 - a∑y - b∑xyn - 2
39.5 - 1.75(15) - .25(51.5)6 - 2
Sy,x = .306
The standard error of the estimate is $306,000 in sales
4 - 35
Prediction Intervals Prediction Intervals
The ranges or limits of a forecast are estimated by:
Upper limit = Y + t*Sy,x
Lower limit = Y - t*Sy,x
where:
Y = forecasted value (point estimate)
t = number of standard deviations from the mean of the distribution to provide a given probability of exceeding the limits through chance
syx = standard error of the forecast
© 2011 Pearson Education, Inc. publishing as Prentice Hall
4 - 36© 2011 Pearson Education, Inc. publishing as Prentice Hall
How strong is the linear relationship between the variables?
Correlation does not necessarily imply causality!
Coefficient of correlation, r, measures degree of association Values range from -1 to +1
CorrelationCorrelation
4 - 37© 2011 Pearson Education, Inc. publishing as Prentice Hall
Correlation CoefficientCorrelation Coefficient
r = nxy - xy
[nx2 - (x)2][ny2 - (y)2]
4 - 38© 2011 Pearson Education, Inc. publishing as Prentice Hall
Multiple Regression Multiple Regression AnalysisAnalysis
If more than one independent variable is to be used in the model, linear regression can be
extended to multiple regression to accommodate several independent variables
y = a + b1x1 + b2x2 …^
Computationally, this is quite Computationally, this is quite complex and generally done on the complex and generally done on the
computercomputer
4 - 39© 2011 Pearson Education, Inc. publishing as Prentice Hall
Multiple Regression Multiple Regression AnalysisAnalysis
y = 1.80 + .30x1 - 5.0x2^
In the Nodel example, including interest rates in the model gives the new equation:
An improved correlation coefficient of r = .96 means this model does a better job of predicting the change in construction sales
Sales = 1.80 + .30(6) - 5.0(.12) = 3.00Sales = $3,000,000
4 - 40© 2011 Pearson Education, Inc. publishing as Prentice Hall
Measures how well the forecast is predicting actual values
Ratio of cumulative forecast errors to mean absolute deviation (MAD) Good tracking signal has low values
If forecasts are continually high or low, the forecast has a bias error
Monitoring and Controlling Monitoring and Controlling ForecastsForecasts
Tracking SignalTracking Signal
4 - 41© 2011 Pearson Education, Inc. publishing as Prentice Hall
Monitoring and Controlling Monitoring and Controlling ForecastsForecasts
Tracking signal
Cumulative errorMAD
=
Tracking signal =
∑(Actual demand in period i -
Forecast demand in period i)
∑|Actual - Forecast|/n)
4 - 42© 2011 Pearson Education, Inc. publishing as Prentice Hall
Tracking SignalTracking Signal
Tracking signal
+
0 MADs
–
Upper control limit
Lower control limit
Time
Signal exceeding limit
Acceptable range
4 - 43© 2011 Pearson Education, Inc. publishing as Prentice Hall
Forecasting in the Service Forecasting in the Service SectorSector
Presents unusual challenges Special need for short term records
Needs differ greatly as function of industry and product
Holidays and other calendar events
Unusual events