Forecasting

Process to Predict the Future

using (time series related or
other) data we have in hand
 Why are we interested?
 Affects the decisions we make today
 Where is forecasting used in POM
 forecast demand for products and
services
 forecast
availability/need for
manpower
 forecast inventory and materiel needs
daily
What Makes a Good Forecast?

 It should be timely
 It should be as accurate as possible
 It should be reliable
 It should be in meaningful units
 It should be presented in writing
 The method should be easy to use and
understand in most cases.
Forecasting time horizons

 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
Types of Forecasts

 Economic forecasts
 Address business cycle – inflation rate,
money supply, housing starts, etc.
 Technological forecasts
 Predict rate of technological progress
 Impacts development of new products
 Demand forecasts
 Predict sales of existing products and
services
Eight Steps to Forecasting
 Determine the use of the forecast
 What objective are we trying to obtain?
 Select the items or quantities that are to be forecasted.
 Determine the time horizon of the forecast.
 Short time horizon – 1 to 30 days
 Medium time horizon – 1 to 12 months
 Long time horizon – more than 1 year
 Select the forecasting model or models
 Gather the data to make the forecast.
 Validate the forecasting model
 Make the forecast
 Implement the results
Forecasting Models

Forecasting
Techniques

Qualitative Time Series

Models Methods

Delphi
Naive
Method
Moving
Jury of Executive
Average
Opinion
Weighted
Sales Force
Moving Average
Composite
Exponential
Consumer Market
Smoothing
Survey

Trend Analysis
Causal
Methods
Seasonality
Simple Analysis
Regression
Analysis
Multiplicative
Decomposition
Multiple
Regression
Analysis
Model Differences

 Qualitative – incorporates
judgmental & subjective factors
into forecast.
 Time-Series – attempts to predict
the future by using historical data.
 Causal – incorporates factors that
may influence the quantity being
forecasted into the model
Qualitative Forecasting
Models
 Delphi method
 Iterative group process allows experts to
make forecasts
 Participants:
 decision makers: 5 -10 experts who make the
forecast
 staff personnel: assist by preparing,
distributing, collecting, and summarizing a
series of questionnaires and survey results
 respondents: group with valued judgments
who provide input to decision makers
Qualitative Forecasting Models (cont)
 Jury of executive opinion
 Opinions of a small group of high level managers, often in
combination with statistical models.
 Result is a group estimate.
 Sales force composite
 Each salesperson estimates sales in his region.
 Forecasts are reviewed to ensure realistic.
 Combined at higher levels to reach an overall forecast.
 Consumer market survey.
 Solicits input from customers and potential customers regarding
future purchases.
 Used for forecasts and product design & planning
Forecast Error
Forecast Error  At  Ft

 Bias - The arithmetic sum of T

the errors MSE   | forecast error | 2 /T
t 1
 Mean Square Error - Similar to
simple sample variance T
  (At  Ft ) 2 / T
 Variance - Sample variance t 1
(adjusted for degrees of
freedom)
 Standard Error - Standard
deviation of the sampling
distribution
 MAD - Mean Absolute T T

Deviation MAD   | forecast error | /T   |At  Ft | / T

t 1 t 1
 MAPE – Mean Absolute
Percentage Error T
MAPE  100 [|At  Ft | / At ] / T
t 1
Quantitative Forecasting Models

 Time Series Method

 Naïve
 Whatever happened
recently will happen
again this time (same Ft  Yt 1
time period)
 The model is simple
and flexible
 Provides a baseline to Ft  Yt  4 : Quarterly data
measure other models
 Attempts to capture
Ft  Yt 12 : Monthly data
seasonal factors at the
expense of ignoring
trend
Naïve Forecast
Wallace Garden Supply
Forecasting
Storage Shed Sales

Actual Naïve Absolute Percent Squared

Period Value Forecast Error Error Error 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% 9.0
November 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

 Quantitative Forecasting Models

 Time Series Method

 Moving Averages
 Assumes item forecasted will stay steady
over time.
 Technique will smooth out short-term
irregularities in the time series.

k
k - period moving average   (Actual value in previous k periods) /k
k 1
Moving Averages
Wallace Garden Supply
Forecasting
Storage Shed Sales

Actual
Period Value Three-Month Moving Averages
January 10
February 12
March 16
April 13 10 + 12 + 16 / 3 = 12.67
May 17 12 + 16 + 13 / 3 = 13.67
June 19 16 + 13 + 17 / 3 = 15.33
July 15 13 + 17 + 19 / 3 = 16.33
August 20 17 + 19 + 15 / 3 = 17.00
September 22 19 + 15 + 20 / 3 = 18.00
October 19 15 + 20 + 22 / 3 = 19.00
November 21 20 + 22 + 19 / 3 = 20.33
December 19 22 + 19 + 21 / 3 = 20.67
Moving Averages Forecast
Wallace Garden Supply
Forecasting 3 period moving average
Actual Value - Forecast

Input Data Forecast Error Analysis

Absolute Squared Absolute
Period Actual Value Forecast Error error error % error
Month 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 12.000 2.000 6.074 10.61%
Next period 19.667 BIAS MAD MSE MAPE
 Quantitative Forecasting
Models
 Time Series Method
 Weighted Moving Averages
 Assumes data from some periods are more
important than data from other periods (e.g.
earlier periods).
 Use weights to place more emphasis on some
periods and less on others.

k - period weighted moving average 

k k

 (Weight
i 1
for each period i)(Actual value in previous k periods) /  (weights)
i 1
Weighted Moving Average
Wallace Garden Supply
Forecasting
Storage Shed Sales

Actual
Period Value Weights Three-Month Weighted Moving Averages
January 10 0.222
February 12 0.593
March 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 = 19.262
November 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

Weighted Moving Average
Wallace Garden Supply
Forecasting 3 period weighted moving average

Input Data Forecast Error Analysis

Absolute Squared Absolute
Period Actual value Weights Forecast Error error error % error
Month 1 10 0.222
Month 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

Quantitative Forecasting
Models
 Time Series Method
 Exponential Smoothing
 Moving average technique that
requires little record keeping of past
data.
 Uses a smoothing constant α with a
value between 0 and 1. (Usual range
0.1 to 0.3)
Forecast for period t 
forecast for period t - 1   (actual value in period t - 1 - forecast for period t - 1)
Exponential Smoothing Data
Wallace Garden Supply
Forecasting
Storage Shed Sales

Exponential Smoothing
Actual
Period Value Ft α At Ft Ft+1
January 10 10 0.1
February 12 10 + 0.1 *( 10 - 10 ) = 10.000
March 16 10 + 0.1 *( 12 - 10 ) = 10.200
April 13 10 + 0.1 *( 16 - 10 ) = 10.780
May 17 11 + 0.1 *( 13 - 11 ) = 11.002
June 19 11 + 0.1 *( 17 - 11 ) = 11.602
July 15 12 + 0.1 *( 19 - 12 ) = 12.342
August 20 12 + 0.1 *( 15 - 12 ) = 12.607
September 22 13 + 0.1 *( 20 - 13 ) = 13.347
October 19 13 + 0.1 *( 22 - 13 ) = 14.212
November 21 14 + 0.1 *( 19 - 14 ) = 14.691
December 19 15 + 0.1 *( 21 - 15 ) = 15.322
Exponential Smoothing
Wallace Garden Supply
Forecasting Exponential smoothing

Input Data Forecast Error Analysis

Absolute Squared Absolute
Period Actual value Forecast Error error error % error
Month 1 10 10.000
Month 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

Trend & Seasonality

 Trend analysis
 technique that fits a trend equation (or curve) to
a series of historical data points.
 projects the curve into the future for medium
and long term forecasts.
 Seasonality analysis
 adjustment to time series data due to variations
at certain periods.
 adjust with seasonal index – ratio of average
value of the item in a season to the overall
annual average value.
 example: demand for coal & fuel oil in winter
months.
Least Squares Method

^
Y  a  bX
Where

^
Y = predicted value of the dependent variable (demand)

X = value of the independent

variable (time)

_ _
a = Y-axis intercept
[ XY - n X Y ]
b=
b = slope of the regression line  _
2
 X - n X 
2

 
Linear Trend Data & Error Analysis
Midwestern Manufacturing Company
Forecasting Linear trend analysis

Input Data Forecast Error Analysis

Actual value Period number Absolute Squared Absolute
Period (or) Y (or) X Forecast Error error error % 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

Seasonality Analysis
Ratio = demand / average demand
Eichler Supplies
Average Seasonal
Year Month Demand Demand Ratio Index
1 January 80 94 0.851 0.957
February 75 94 0.798 0.851
Seasonal Index – ratio of the
March 80 94 0.851 0.904 average value of the item in a
April 90 94 0.957 1.064 season to the overall average
May 115 94 1.223 1.309
June 110 94 1.170 1.223
annual value.
July 100 94 1.064 1.117
August 90 94 0.957 1.064 Example: average of year 1
September 85 94 0.904 0.957
October 75 94 0.798 0.851 January ratio to year 2 January
November 75 94 0.798 0.851 ratio.
December 80 94 0.851 0.851
(0.851 + 1.064)/2 = 0.957
2 January 100 94 1.064
February 85 94 0.904
March 90 94 0.957
April 110 94 1.170 If Year 3 average monthly demand is
May 131 94 1.394
June 120 94 1.277 expected to be 100 units.
July 110 94 1.170 Forecast demand Year 3 January:
August 110 94 1.170 100 X 0.957 = 96 units
September 95 94 1.011 Forecast demand Year 3 May:
October 85 94 0.904
100 X 1.309 = 131 units
November 85 94 0.904
December 80 94 0.851
Deseasonalized Data
 Going back to the conceptual model, solve for trend:
 Trend = Y / Season (96 units/
0.957 = 100.31)
 This eliminates seasonal variation and isolates the
trend
 Now use the Least Squares method to compute the
Trend
Forecast
 Now that we have the Seasonal Indices and Trend, we
can reseasonalize the data and generate the forecast
 Y = Trend x Seasonal Index
 “The most reliable way to
forecast the future is to try
to understand the present.”

-John Naisbitt