Industrial Automation

1. 1
Forecasting

2. 2
Learning Objectives
■ Definition of forecasting
■ Importance and need of forecasting
■ Identify Principles of Forecasting
■ Explain the steps in the forecasting
process
■ Identify types of forecasting methods and
their characteristics
■ Describe time series and causal models

3. © Wiley 2010 3
Learning Objectives con’t
■ Generate forecasts for data with different
patterns: level, trend, seasonality, and
cyclical
■ Describe causal modeling using linear
regression
■ Compute forecast accuracy
■ Explain how forecasting models should be
selected

4. © Wiley 2010 4
Forecasting definition
■ Forecasting is a process of estimating the
future demand in terms of the quality,
timing and location for desired product
and services.
■ Forecasting is an art and science of
predicting future events.
■ Forecasting is a tool used for predicting
the future demand based on past demand
information

5. © Wiley 2010 5
Forecasting

6. © Wiley 2010 6
Need of Forecasting
■ Lead times require that decision be made
in advance of uncertain events.
■ Forecasting is important for all strategic
and planning decisions in a supply chain
■ Forecasts of product demand, materials,
labor, financing are an important inputs
to acquiring resources and determining
resource requirements.

7. Need for Forecasting
■ Balancing supply and demand
■ Useful at both supply chain and process
level.
■ Input to business plans, budgets
■ Needed to project the hiring and training
needs, cash flow requirements
■ To plan purchase of materials, inventory,
long term capacities, output levels,
schedules © Wiley 2010 7

8. Forecasting Horizons
■ Short Term (0 to 3 months): for
inventory management and scheduling.
■ Medium Term (3 months to 2 years): for
production planning and distribution.
■ Long Term (2 years and more): for
capacity planning, facility location and
strategic planning.
© Wiley 2010 8

9. Key issues in Forecasting
■ A forecast is only as good as the
information included in the forecast (past
data)
■ History is not the perfect predictor of
future (i.e. there is no such thing as a
perfect forecast) © Wiley 2010 9

10. What should we consider when looking at past
demand data
■ Trends
■ Seasonality
■ Cyclical elements
■ Random variation
© Wiley 2010 10

11. Forecasting System
■ As an activity within an organization, forecasting is expected
to provide relevant information concerning the future to
marketing, finance and others that require it for planning
purpose.
■ This function id performed by a system which, like any
other system can be analyzed in terms of its key
components.
© Wiley 2010 11

12. Forecasting System
■ Forecasting system outputs: Information provided by a
forecast
■ Forecasting system inputs: information needed to
prepare a forecast
■ Forecasting system constraints: Factors limiting the
methods used.
■ Forecasting system decisions:
© Wiley 2010 12

13. Forecasting System
■ Forecasting system performance criteria
■ Forecasting methods
© Wiley 2010 13

14. Forecasting System
© Wiley 2010 14

15. Forecasting System Outputs
© Wiley 2010 15
■ From the production manager points of view,
what is needed to plan for different periods in
the future is a forecast of expected demand
rather than future sales.
■ Demand relates to orders received from
customers, while sales refers to shipment made,
Demand thus sometimes differ from due to
limited capacity (thus lost sales) or in the timing
or shipments due to production lead time

16. Forecasting System Inputs
© Wiley 2010 16
■ The data needed to prepare a demand forecast
can be obtained from internal/ or external
source.
■ Historical data in the form of a time series on
previous sales or orders, expert’s opinions of an
organization personnel and results of especial
surveys are the most frequently used
information inputs that can be generated within
the organization.

17. Forecasting System Constraints
© Wiley 2010 17
■ The selection of the forecasting method and the
value of the forecasts prepared depends heavily
on the constraints imposed on the forecasting
system such as:
I. Time available to prepare a forecast
II. Lack of relevant data available from internal
and external sources
III. The quality of data available
IV. The expertise within the organization

18. Forecasting System Decisions
© Wiley 2010 18
■ In operating a forecasting system, management
must make decisions with respect to the data
and methods that will be used to develop a
forecast.
■ The data may be in the form needed or may
require adjustment or aggregation, if there is a
long history of demand, care must be exercised
with regard to “how far back to go”.

19. Forecasting System Performance
Criteria
© Wiley 2010 19
■ The effectiveness of the forecasting system in
serving the organization can be evaluated on the
basis of three criteria:
I. Accuracy
II. Objectivity in the treatment of historical data
III. Time require to prepare forecast

20. © Wiley 2010 20
Principles of Forecasting
Many types of forecasting models that differ
in complexity and amount of data & way
they generate forecasts:
1. Forecasts are rarely perfect
2. Forecasts are more accurate for grouped
data than for individual items
3. Forecast are more accurate for shorter
than longer time periods

21. © Wiley 2010 21
Forecasting methods
■ Qualitative Methods: are subjective in nature
since they rely on human judgment and
opinions.
■ Quantitative Methods: use mathematical or
simulation models based on historical demand
or relationship between variables

22. © Wiley 2010 22
Qualitative or subjective
■ Rely primarily on the experience and opinions
of people inside or outside the organization.
■ Employed either when there is little time or no
past relevant data
■ Introducing a new product represents activity
with limited or non-existent historical data.
■ Major application in long range strategic
planning.

23. © Wiley 2010 23
Subjective-Estimate survey
■ Forecast draws on the experience, knowledge
and the sixth sense of their own people.
■ Individual salesmen asked to submit estimates
of anticipated demand.
■ These estimates are pooled at the regional level
and adjusted to account for regional, economic,
demographic and other factors.

24. © Wiley 2010 24
Drawbacks of surveys
■ Allow recent experiences to play a more
dominant influence than they should.
■ Dominant personalities can produce estimates
that depart from general consensus.
■ The lack of any measure of accuracy in the
estimate, difficult to plan how to cope with
large errors.

25. © Wiley 2010 25
The Delphi Method

26. © Wiley 2010 26
Types of Forecasting Methods
■ Forecasting methods are classified into
two groups:

27. © Wiley 2010 27
Types of Forecasting Models
■ Qualitative methods – judgmental methods
■ Forecasts generated subjectively by the
forecaster
■ Educated guesses
■ Quantitative methods – based on
mathematical modeling:
■ Forecasts generated through mathematical
modeling

28. © Wiley 2010 28
Qualitative Methods

29. © Wiley 2010 29
Quantitative Methods
■ Time Series Models:
■ Assumes information needed to generate a
forecast is contained in a time series of data
■ Assumes the future will follow same patterns as
the past
■ Causal Models or Associative Models
■ Explores cause-and-effect relationships
■ Uses leading indicators to predict the future
■ Housing starts and appliance sales

30. © Wiley 2010 30
Time Series Patterns

31. © Wiley 2010 31
Time Series Models
■ Forecaster looks for data patterns as
■ Data = historic pattern + random variation
■ Historic pattern to be forecasted:
■ Level (long-term average) – data fluctuates around a constant
mean
■ Trend – data exhibits an increasing or decreasing pattern
■ Seasonality – any pattern that regularly repeats itself and is of a
constant length
■ Cycle – patterns created by economic fluctuations
■ Random Variation cannot be predicted

32. © Wiley 2010 32
Time Series Models

33. Time series methods
■ Simple Mean:
■ The average of all available data - good for level patterns
■ Moving Average:
■ Using demand for n most recent periods for next period
forecast
■ Each new forecast drops the oldest data point & adds a
new observation
■ More responsive to a trend but still lags behind actual
data
© Wiley 2010 33

34. Moving Average method
■ Forecast for next period (Ft+1)
Ft+1 = Dt+Dt-1+……Dt-n+1/n
If the demand in week 1,2,3 is 400, 380 and 411
respectively and n=3, then
Forecast for week 4= (411+380+400)/3=397
If demand for week 4 is 415, then F5 is,
F5= 415+411+380/3= 402
■ Large values of n should be used for stable demand
series and small values for fluctuating demand
© Wiley 2010 34

35. © Wiley 2010 35
Time Series Models con’t
■ Weighted Moving Average:
■ All weights must add to 100% or 1.00
e.g. Ct .5, Ct-1 .3, Ct-2 .2 (weights add to 1.0)
■ Allows emphasizing most recent period over others;
above indicates more weight on recent data (Ct=.5)
■ Differs from the simple moving average that weighs
all periods equally - more responsive to trends

36. © Wiley 2010 36
Example

37. © Wiley 2010 37
Example

38. © Wiley 2010 38
Example

39. © Wiley 2010 39
Example

40. © Wiley 2010 40
Example

41. © Wiley 2010 41
Example

42. © Wiley 2010 42
Example

43. © Wiley 2010 43
Exponential Smoothing
Method
■ Includes all past observations
■ More weights are given to the recent
observations and less weights are given to
the old observations.

44. © Wiley 2010 44
Exponential Smoothing
Method

45. Exponential smoothening
method
■ The emphasis given to most recent
period’s demand may be adjusted by
changing the value of
■ Large values of α result in more
responsive forecast to a trend in data
■ Small values of α generate a stable type
forecast.
■ Forecasts will still lag the demand if the
average is shifting systematically 45

46. © Wiley 2010 46
Time Series Problem Solution

47. © Wiley 2010 47
Time Series Problem Solution

48. © Wiley 2010 48
Time Series Problem
■ Determine forecast for
periods 7 & 8
■ 2-period moving average
■ 4-period moving average
■ 2-period weighted moving
average with t-1 weighted 0.6
and t-2 weighted 0.4
■ Exponential smoothing with
alpha=0.2 and the period 6
forecast being 375
Period Actual
1 300
2 315
3 290
4 345
5 320
6 360
7 375
8

49. © Wiley 2010 49
Time Series Problem Solution
Period Actual 2-Period 4-Period 2-Per.Wgted. Expon. Smooth.
1 300 0 0
2 315 0 0
3 290 307.5
4 345 302.5
5 320 317.5
6 360 332.5
7 375 340.0 328.8 344.0 372.0
8 367.5 350.0 369.0 372.6

50. 50
Causal Models
■ Causal models establish a cause-and-effect
relationship between independent and dependent
variables (i.e. demand and parameters related to
demand)
■ The objective is to find the change in the demand
level due to corresponding change in the input
parameters.
■ A common tool of causal modeling is linear
regression:
■ Additional related variables may require multiple
regression modeling

51. 51
Linear Regression
■ A method for obtaining the
line of best fit between the
dependent and independent
variables.
■ Dependent variable is
demand and the
independent variables are
variables that affects the
demand.
■ The relationship between
dependent variable Y and
independent variable X can
be represented by
■ Y=a + bX

52. 52
Linear Regression

53. 53
Linear Regression

54. © Wiley 2010 54
Linear Regression
■ Identify dependent (y) and
independent (x) variables
■ Solve for the slope of the
line
■ Solve for the y intercept
■ Develop your equation for
the trend line
Y=a + bX

55. 55
Linear Regression

56. 56
Linear Regression

57. © Wiley 2010 57
Linear Regression Problem: A maker of golf shirts has been
tracking the relationship between sales and advertising dollars. Use
linear regression to find out what sales might be if the company
invested $53,000 in advertising next year.
Sales $
(Y)
Adv.$
(X)
XY X^2 Y^2
1 130 32 4160 2304 16,900
2 151 52 7852 2704 22,801
3 150 50 7500 2500 22,500
4 158 55 8690 3025 24964
5 153.85 53
Tot 589 189 28202 9253 87165
Avg 147.25 47.25

58. © Wiley 2010 58
Correlation Coefficient
How Good is the Fit?
■ Correlation coefficient (r) measures the direction and strength of the linear
relationship between two variables. The closer the r value is to 1.0 the better
the regression line fits the data points.
■ Coefficient of determination ( ) measures the amount of variation in the
dependent variable about its mean that is explained by the regression line.
Values of ( ) close to 1.0 are desirable.

59. © Wiley 2010 59
Measuring Forecast Error
■ Forecasts are never perfect
■ Need to know how much we should
rely on our chosen forecasting method
■ Measuring forecast error:
■ Note that over-forecasts = negative
errors and under-forecasts = positive
errors

60. © Wiley 2010 60
Measuring Forecasting Accuracy
■ Mean Absolute Deviation (MAD)
■ measures the total error in a
forecast without regard to sign
■ Cumulative Forecast Error (CFE)
■ Measures any bias in the forecast
■ Mean Square Error (MSE)
■ Penalizes larger errors
■ Tracking Signal
■ Measures if your model is working

61. © Wiley 2010 61
Accuracy & Tracking Signal Problem: A company is comparing the
accuracy of two forecasting methods. Forecasts using both methods are
shown below along with the actual values for January through May. The
company also uses a tracking signal with ±4 limits to decide when a
forecast should be reviewed. Which forecasting method is best?
Month Actual
sales
Method A Method B
F’cast Error Cum.
Error
Tracking
Signal
F’cast Error Cum.
Error
Tracking
Signal
Jan. 30 28 2 2 2 27 2 2 1
Feb. 26 25 1 3 3 25 1 3 1.5
March 32 32 0 3 3 29 3 6 3
April 29 30 -1 2 2 27 2 8 4
May 31 30 1 3 3 29 2 10 5
MAD 1 2
MSE 1.4 4.4

62. © Wiley 2010 62
Selecting the Right Forecasting Model
1. The amount & type of available data
▪ Some methods require more data than others
2. Degree of accuracy required
▪ Increasing accuracy means more data
3. Length of forecast horizon
▪ Different models for 3 month vs. 10 years
4. Presence of data patterns
▪ Lagging will occur when a forecasting model
meant for a level pattern is applied with a trend