Operations Management
Forecasting
Models & Their Applications
OperationsManagement
Lecture Outline
 Definitions of forecasting
 Roles of Forecasting and applications
 Components of Forecasting Demand
 List the elements of a good forecast
 The steps in the forecasting process
 Compare and contrast qualitative and
quantitative approaches to forecasting
 Advantages and disadvantages of each
 Time Series Methods
 Forecast Accuracy
 Time Series Forecasting Using Excel (if possible)
 Regression Methods
Forecasting: Models and Applications
OperationsManagement
Forecasting ?
• Predicting the future based on the historical data.
• A statement about the future value of a variable of interest
such as demand.
• Forecasting is used to make informed decisions.
- Long-range
- Short-range
 It is the basis for budgeting, planning capacity, sales,
production and inventory, personnel, purchasing, and more.
Forecasts play an important role in the planning process to
anticipate the future plan accordingly.
Forecasting: Models and Applications
Forecasting
OperationsManagement
Data based - expecting that history repeats itself in a certain
way; usually given in the form of a time series, a
chronological sequence of observed data with respect to a
certain variable.
Theory based - where the external factors determine events.
Qualitative forecast methods
- subjective
Quantitative forecast methods
- based on mathematical formulas
Types of Forecasting
Two main methods:
Another distinction consists of:
Forecasting: Models and Applications
OperationsManagement
Decisions and activities throughout an organization
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
Uses of Forecasting
Forecasting: Models and Applications
OperationsManagement
• Assumes causal system
Past => Present => Future
• Forecasts rarely perfect because of randomness
• Forecasts more accurate for groups vs. individuals
• Forecast accuracy decreases as time horizon increases
Features of Forecasting
Forecasting: Models and Applications
I see that you will
get an A this semester.Timely
AccurateReliable
Written
Elements of a
Good Forecast
OperationsManagement
Depend on
• time frame
• demand behavior
• causes of behavior
Indicates how far into the future is forecast
• Short- to mid-range forecast
• typically encompasses the immediate future
• daily up to two years
• Long-range forecast
• usually encompasses a period of time longer
than two years
Types of Forecasting Methods
Time Frame
Forecasting: Models and Applications
OperationsManagement
 Trend
• a gradual, long-term up or down movement of
demand
 Random variations
• movements in demand that do not follow a pattern
 Cycle
• an up-and-down repetitive movement in demand
 Seasonal pattern
• an up-and-down repetitive movement in demand
occurring periodically
Demand Behavior
Types of Forecasting Methods
Forecasting: Models and Applications
OperationsManagement
Time
(a) Trend
Time
(d) Trend with seasonal pattern
Time
(c) Seasonal pattern
Time
(b) Cycle
DemandDemand
DemandDemand
Random
movement
Demand Behavior
Types of Forecasting Methods
Forecasting: Models and Applications
OperationsManagement
Types of Forecasting Methods
 Time series
• statistical techniques that use historical demand
data to predict future demand
 Regression methods
• attempt to develop a mathematical relationship
between demand and factors that cause its behavior
 Qualitative
• use management judgment, expertise, and opinion
to predict future demand
Regular Behavior
Forecasting: Models and Applications
OperationsManagement
Steps of Forecasting Technique
Forecasting: Models and Applications
Step 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
“The forecast”
OperationsManagement Forecasting: Models and Applications
6. Check forecast
accuracy with one
or more measures
4. Select a forecast
model that seems
appropriate for data
5. Develop/compute
forecast for period
of historical data
8a. Forecast over
planning horizon
9. Adjust forecast
based on additional
qualitative information
and insight
10. Monitor results
and measure
forecast accuracy
8b. Select new
forecast model or
adjust parameters
of existing model
7.
Is accuracy
of forecast
acceptable?
1. Identify the
purpose of forecast
3. Plot data and
identify patterns
2. Collect
historical data
No
Yes
Copyright 2011 John Wiley & Sons, Inc.
Steps of Forecasting Technique
OperationsManagement Forecasting: Models and Applications
 Judgmental
- uses subjective inputs for qualitative methods
 Time series
- uses historical data assuming the future will be like
the past or present data
 Associative models
- uses explanatory variables to predict the future
Forecasting Techniques
OperationsManagement Forecasting: Models and Applications
Forecasts are largely intuitive, whereas others integrate data
and perhaps even mathematical or statistical techniques.
Judgmental forecasts consist of:
 forecasts by experts in the same field,
 forecasts by individual sales people,
 forecasts by division or product-line managers,
 consumer surveys,
 outside/ external experts or technical reports
Historical analogy relies on comparisons; Delphi method
o Opinions of managers and staff
o Achieves a consensus forecast
Opinion and Judgmental Methods
Forecasting Techniques
OperationsManagement Forecasting: Models and Applications
Forecasting Techniques
Time series Analysis
 A time series is a set of observations of a variable at
regular intervals over time.
 Assume that what has occurred in the past will continue
to occur in the future.
 Components of a time series are generally classified as
trend T, cyclical C, seasonal S, and random or irregular R.
 Time series analysis includes:
• moving average
• exponential smoothing
• linear trend line
 Data are tabulated or graphed to show the nature of the
time dependence.
OperationsManagement Forecasting: Models and Applications
Following are the steps in time series forecasting:
1. Plot historical data to confirm relationship (e.g.,
linear, exponential, logarithmic etc).
2. Develop a trend equation (T ) to describe the data.
3. Develop a seasonal index (e.g., monthly index values).
4. Project trend into the future (e.g., monthly trend values).
5. Multiply trend values by corresponding seasonal
index values.
6. Modify projected values by any knowledge of:
• Cyclical business conditions (C) ,
• Anticipated irregular effects (R) .
Time series forecasting procedure
Forecasting Techniques
OperationsManagement
 Simple to use
 Virtually no cost
 Quick and easy to prepare
 Data analysis is nonexistent
 Easily understandable
 Cannot provide high accuracy
 Can be a standard for accuracy
Naïve Forecasts
Forecasting Techniques
 The forecast for any period equals the previous period’s
actual value.
 Demand in current period is used as next period’s
forecast
Why Naïve Forecasts ?
Uh, give me a minute....
We sold 250 wheels last week....
Now, next week we should
sell.... 250???
Forecasting: Models and Applications
OperationsManagement
Forecasting Techniques
Forecasting: Models and Applications
Jan 120
Feb 90
Mar 100
Apr 75
May 110
June 50
July 75
Aug 130
Sept 110
Oct 90
ORDERS
Month Per Month
-
120
90
100
75
110
50
75
130
110
90Nov - ??
Forecast
Naïve Forecasts
Mathematical formula
used in Naïve:
• Stable time series
data
F (t ) = A (t -1)
• Seasonal variations
F (t ) = A (t – n )
• Data with trends
F (t ) = A ( t - 1) +
(A (t -1) – A(t – 2 ))
OperationsManagement
Three methods for describing trend are:
1. Moving average,
2. Hand fitting, and
3. Least squares.
A centered moving average is obtained by summing and
averaging the values from a given number of periods
repetitively, each time deleting the oldest value and adding
a new value.
Moving averages can smooth out fluctuations in any data,
while preserving the general pattern of the.
Forecasting Techniques
Trend Technique
Moving Average Method:
Forecasting: Models and Applications
OperationsManagement
The generalized formula for moving average method is:
 Moving average / simple moving average
 Weighted moving average
 Exponential smoothing
Moving Average Method Cont…
𝑴𝑨 =
𝒙
Number of Period
Techniques for Averaging
– Averaging method
– Weights most recent data more strongly
– Reacts more to recent changes
– Widely used, accurate method
Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement
A technique that averages a number of recent actual
values, updated as new values become available.
MAn =
n
i = 1

Di
n
Simple Moving average
where
n = number of periods
in the moving
average
Di = demand in period i
Ft = MAn=
n
At-n + … At-2 + At-1
Or,
Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement
3-month Simple Moving Average
Jan 120
Feb 90
Mar 100
Apr 75
May 110
June 50
July 75
Aug 130
Sept 110
Oct 90
Nov -
Orders
Month Per Month
MA3 =
3
i = 1
 Di
3
=
90 + 110 + 130
3
= 110 orders for Nov
–
–
–
103.3
88.3
95.0
78.3
78.3
85.0
105.0
110.0
Moving
Average
Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement
Jan 120
Feb 90
Mar 100
Apr 75
May 110
June 50
July 75
Aug 130
Sept 110
Oct 90
Nov -
Orders
Month Per Month
–
–
–
–
–
99.0
85.0
82.0
88.0
95.0
91.0
Moving
Average
5-month Simple Moving Average
MA5 =
5
i = 1
 Di
5
=
90 + 110 + 130+75+50
5
= 91 orders for Nov
Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement
150 –
125 –
100 –
75 –
50 –
25 –
0 – | | | | | | | | | | |
Jan Feb Mar Apr May June July Aug Sept Oct Nov
Actual
Orders
Month
5-month
3-month
Effect of 3-month and 5-month moving average
Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement
 More recent values in a series are given more weight in
computing the forecast.
 Adjusts moving average method to more closely reflect
data fluctuations
Weighted Moving Average
WMAn =
i = 1
 Wi Di
where
Wi = the weight for period i,
between 0 and 100 %
Wi = 1.00
n
Ft = WMAn=
wnAt-n + … wn-1At-2 + w1At-1
n
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
MONTH WEIGHT DATA
August 17% 130
September 33% 110
October 50% 90
WMA3 =
3
i = 1
 Wi Di
= (0.50)(90) + (0.33)(110) + (0.17)(130)
= 103.4 orders
November Forecast
Forecasting Techniques
Forecasting: Models and Applications
Example: Weighted Moving Average
OperationsManagement Forecasting: Models and Applications
Example: Weighted Moving Average
Forecasting Techniques
Shipments (in tons) of welded tube by an aluminum producer
are shown below:
a) Graph the data, and comment on the relationship.
b) Compute a 3-year moving average, plot it as a dotted
line, and use it to forecast shipments in year 12.
c) Using a weight of 3 for the most recent data, 2 for
the next, and 1 for the oldest, forecast shipments in
year 12.
Ref. Operations management, A. Kumar and N. Suresh, New Age, pp. 108-109
OperationsManagement
Solution:
Year Shipments 3-y moving
average
1 2 -
2 3 3.7
3 6 6.3
4 10 8.0
5 8 8.3
6 7 9.0
7 12 11.0
8 14 13.3
9 14 15.3
10 18 17.0
11 19 -
The MA forecast for year 12 would be
that of the latest average, 17.0 tons.
The data are plotted as shown:
Moving average:
= 17.8 tons
Example: WMA Cont…
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
The equation used for forecast for next period is:
where:
Ft +1 = forecast for next period
Dt = actual demand for present period
Ft = previously determined forecast for present period
𝜶 = weighting factor, smoothing constant
Exponential Smoothing
𝑭 𝒕+𝟏 = 𝜶𝑫 𝒕 + 𝟏 − 𝜶 𝑭 𝒕
Effect of Smoothing Constant
0.0  1.0
If = 0.20, then Ft +1 = 0.20 Dt + 0.80 Ft If = 0, then Ft +1 = 0 Dt + 1 Ft = Ft
Forecast does not reflect recent data
If = 1, then Ft +1 = 1 Dt + 0 Ft = Dt ; Forecast based only on most recent data
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
Example: Exponential Smoothing
Period Month Demand
1 Jan 37
2 Feb 40
3 Mar 41
4 Apr 37
5 May 45
6 Jun 50
7 Jul 43
8 Aug 47
9 Sep 56
10 Oct 52
11 Nov 55
12 Dec 54
F2 = D1 + (1 - )F1
= (0.30)(37) + (0.70)(37)
= 37
F3 = D2 + (1 - )F2
= (0.30)(40) + (0.70)(37)
= 37.9
F13 = D12 + (1 - )F12
= (0.30)(54) + (0.70)(50.84)
= 51.79
Letting,  =0.30
and so on. Similarly …
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
Forecast, Ft + 1
Period Month Demand ( = 0.3) ( = 0.5)
1 Jan 37 – –
2 Feb 40 37.00 37.00
3 Mar 41 37.90 38.50
4 Apr 37 38.83 39.75
5 May 45 38.28 38.37
6 Jun 50 40.29 41.68
7 Jul 43 43.20 45.84
8 Aug 47 43.14 44.42
9 Sep 56 44.30 45.71
10 Oct 52 47.81 50.85
11 Nov 55 49.06 51.42
12 Dec 54 50.84 53.21
13 Jan – 51.79 53.61
Example: Exponential Smoothing
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
70 –
60 –
50 –
40 –
30 –
20 –
10 –
0 – | | | | | | | | | | | | |
1 2 3 4 5 6 7 8 9 10 11 12 13
Actual
Orders
Month
 = 0.50
 = 0.30
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
Parabolic
Exponential
Growth
Common Nonlinear Trends
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
The generalized equation
y = a + bx
Where,
a = intercept
b = slope of the line
x = time period
y = forecast for
demand for period x
where
n = number of periods
= mean of the x values
= mean of the y values
𝒃 =
𝒙𝒚 − 𝒏. 𝒙. 𝒚
𝒙 𝟐 − 𝒏 𝒙 𝟐
𝒂 = 𝒚 − 𝒃 𝒙
𝒙 =
𝒙
𝒏
𝒚 =
𝒚
𝒏
Linear Trend Line
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
Example: Linear Trend Line
x(Period) y(Demand) xy x2
1 73 37 1
2 40 80 4
3 41 123 9
4 37 148 16
5 45 225 25
6 50 300 36
7 43 301 49
8 47 376 64
9 56 504 81
10 52 520 100
11 55 605 121
12 54 648 144
78 557 3867 650
𝒙 =
𝟕𝟖
𝟏𝟐
= 𝟔. 𝟓 𝒚 =
𝟓𝟓𝟕
𝟏𝟐
= 𝟒𝟔. 𝟒𝟐
𝒃 =
𝒙𝒚−𝒏. 𝒙. 𝒚
𝒙 𝟐−𝒏 𝒙 𝟐 = 1.72
𝒂 = 𝒚 − 𝒃 𝒙
= 𝟒𝟔. 𝟒𝟐 − 𝟏. 𝟕𝟐 × 𝟔. 𝟓 = 𝟑𝟓. 𝟐
Linear trend line y = 35.2 + 1.72x
Forecast for period 13, y = 57.56 units
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
 Linear regression
• mathematical technique that relates a dependent
variable to an independent variable in the form of a
linear equation
 Correlation
• a measure of the strength of the relationship between
independent and dependent variables
Regression Method
The generalized equation, y = a + bx
Where, a = intercept, b = slope of the line, x = time
period, and y = forecast for demand for period x
Linear Regression
n = number of periods𝒃 =
𝒙𝒚 − 𝒏. 𝒙. 𝒚
𝒙 𝟐 − 𝒏 𝒙 𝟐
𝒂 = 𝒚 − 𝒃 𝒙
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
From data,
𝒙 = 𝟔. 𝟏𝟐𝟓
X
wins
Y
attendance
xy x2
4 36.3 145.2 16
6 40.1 240.6 36
6 41.2 247.2 36
8 53.0 424.0 64
6 44.0 264.0 36
7 45.6 319.2 49
5 39.0 195.0 25
7 47.5 332.5 49
49 346.7 2167.7 311
𝒚 = 𝟒𝟑. 𝟑𝟔
𝒃 = 𝟒. 𝟎𝟔 𝒂 = 𝟏𝟖. 𝟒𝟔
Example: Linear Regression
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
 Correlation, r
• Measure of strength of relationship
• Varies between -1.00 and +1.00
 Coefficient of determination, r2
• Percentage of variation in dependent variable resulting
from changes in the independent variable
Computing coefficient of correlation:
Forecasting Techniques
Forecasting: Models and Applications
Correlation
n xy -  x y
[n x2 - ( x)2] [n y2 - ( y)2]
r =
(8)(2,167.7) - (49)(346.9)
[(8)(311) - (49)2] [(8)(15,224.7) - (346.9)2]
r = =0.947
OperationsManagement
Multiple Regression
Study the relationship of demand to two or more independent
variables
The relationship is expressed as:
y = 0 + 1x1 + 2x2 … + kxk
where
0 = the intercept
1, … , k = parameters for the independent variables
x1, … , xk = independent variables
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
r2, the coefficient
of determination
Regression equation
coefficients for x1 and x2
Multiple Regression
Forecasting Techniques
Forecasting: Models and Applications
y = 19,094.42 + 3560.99 x1 + .0368 x2
y = 19,094.42 + 3560.99 (7) + .0368 (60,000)
= 46,229.35
OperationsManagement
Seasonal Adjustments
Forecasting Techniques
• Repetitive increase/ decrease in demand
• Use seasonal factor to adjust forecast
Seasonal factor = Si =
Di
D
year Demand ( in 1000 units)
1 2 3 4
2002 12.686 6.3 17.5 45.0
2003 14.110 7.5 18.2 50.1
2004 15.31 8.1 19.6 53.6
Total 42.029 21.9 55.3 148.7
𝑆1 =
𝐷1
𝐷
=
42.029
148.7
= 0.28
𝑆4 =
55.3
148.7
= 0.37
𝑆3 =
21.9
148.7
= 0.15
𝑆2 = 0.20
SF1 = (S1) (F5) = (0.28)(58.17) = 16.28
SF2 = (S2) (F5) = (0.20)(58.17) = 11.63
SF3 = (S3) (F5) = (0.15)(58.17) = 8.73
SF4 = (S4) (F5) = (0.37)(58.17) = 21.53
y = 40.97 + 4.30x =
40.97 + 4.30(4) = 58.17
For 2005
Forecasting: Models and Applications
OperationsManagement
=B5*(C11-C10)+
(1-B5)*D10
=C10+D10
=ABS(B10-E10)
=SUM(F10:F20)
=G22/11
Exponentially Smoothing using Excel
Forecasting Techniques
Forecasting: Models and Applications
OperationsManagement
Click on “Insert” then “Line”
Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement
=INTERCEPT(B5:B12,A5:A12)
=CORREL(B5:B12,A5:A12)=SUM(B5:B12)
Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement Forecasting: Models and Applications
Forecasting Techniques
OperationsManagement
 No single technique works in every situation
 Two most important factors
o Cost and Accuracy
 Other factors include the availability of:
 Historical data
 Computers
 Time needed to gather and analyze the data
 Forecast horizon
 Forecasts are the basis for many decisions
 Work to improve short-term forecasts
 Accurate short-term forecasts improve
• Profits
• Lower inventory levels
• Reduce inventory shortages
• Improve customer service levels
• Enhance forecasting credibility
Forecasting: Models and Applications
Choosing Forecasting Tech
OperationsManagement
Effect of Bad Forecasting
Forecasting: Models and Applications

Forecasting Models & Their Applications

  • 1.
  • 2.
    OperationsManagement Lecture Outline  Definitionsof forecasting  Roles of Forecasting and applications  Components of Forecasting Demand  List the elements of a good forecast  The steps in the forecasting process  Compare and contrast qualitative and quantitative approaches to forecasting  Advantages and disadvantages of each  Time Series Methods  Forecast Accuracy  Time Series Forecasting Using Excel (if possible)  Regression Methods Forecasting: Models and Applications
  • 3.
    OperationsManagement Forecasting ? • Predictingthe future based on the historical data. • A statement about the future value of a variable of interest such as demand. • Forecasting is used to make informed decisions. - Long-range - Short-range  It is the basis for budgeting, planning capacity, sales, production and inventory, personnel, purchasing, and more. Forecasts play an important role in the planning process to anticipate the future plan accordingly. Forecasting: Models and Applications Forecasting
  • 4.
    OperationsManagement Data based -expecting that history repeats itself in a certain way; usually given in the form of a time series, a chronological sequence of observed data with respect to a certain variable. Theory based - where the external factors determine events. Qualitative forecast methods - subjective Quantitative forecast methods - based on mathematical formulas Types of Forecasting Two main methods: Another distinction consists of: Forecasting: Models and Applications
  • 5.
    OperationsManagement Decisions and activitiesthroughout an organization 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 Uses of Forecasting Forecasting: Models and Applications
  • 6.
    OperationsManagement • Assumes causalsystem Past => Present => Future • Forecasts rarely perfect because of randomness • Forecasts more accurate for groups vs. individuals • Forecast accuracy decreases as time horizon increases Features of Forecasting Forecasting: Models and Applications I see that you will get an A this semester.Timely AccurateReliable Written Elements of a Good Forecast
  • 7.
    OperationsManagement Depend on • timeframe • demand behavior • causes of behavior Indicates how far into the future is forecast • Short- to mid-range forecast • typically encompasses the immediate future • daily up to two years • Long-range forecast • usually encompasses a period of time longer than two years Types of Forecasting Methods Time Frame Forecasting: Models and Applications
  • 8.
    OperationsManagement  Trend • agradual, long-term up or down movement of demand  Random variations • movements in demand that do not follow a pattern  Cycle • an up-and-down repetitive movement in demand  Seasonal pattern • an up-and-down repetitive movement in demand occurring periodically Demand Behavior Types of Forecasting Methods Forecasting: Models and Applications
  • 9.
    OperationsManagement Time (a) Trend Time (d) Trendwith seasonal pattern Time (c) Seasonal pattern Time (b) Cycle DemandDemand DemandDemand Random movement Demand Behavior Types of Forecasting Methods Forecasting: Models and Applications
  • 10.
    OperationsManagement Types of ForecastingMethods  Time series • statistical techniques that use historical demand data to predict future demand  Regression methods • attempt to develop a mathematical relationship between demand and factors that cause its behavior  Qualitative • use management judgment, expertise, and opinion to predict future demand Regular Behavior Forecasting: Models and Applications
  • 11.
    OperationsManagement Steps of ForecastingTechnique Forecasting: Models and Applications Step 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 “The forecast”
  • 12.
    OperationsManagement Forecasting: Modelsand Applications 6. Check forecast accuracy with one or more measures 4. Select a forecast model that seems appropriate for data 5. Develop/compute forecast for period of historical data 8a. Forecast over planning horizon 9. Adjust forecast based on additional qualitative information and insight 10. Monitor results and measure forecast accuracy 8b. Select new forecast model or adjust parameters of existing model 7. Is accuracy of forecast acceptable? 1. Identify the purpose of forecast 3. Plot data and identify patterns 2. Collect historical data No Yes Copyright 2011 John Wiley & Sons, Inc. Steps of Forecasting Technique
  • 13.
    OperationsManagement Forecasting: Modelsand Applications  Judgmental - uses subjective inputs for qualitative methods  Time series - uses historical data assuming the future will be like the past or present data  Associative models - uses explanatory variables to predict the future Forecasting Techniques
  • 14.
    OperationsManagement Forecasting: Modelsand Applications Forecasts are largely intuitive, whereas others integrate data and perhaps even mathematical or statistical techniques. Judgmental forecasts consist of:  forecasts by experts in the same field,  forecasts by individual sales people,  forecasts by division or product-line managers,  consumer surveys,  outside/ external experts or technical reports Historical analogy relies on comparisons; Delphi method o Opinions of managers and staff o Achieves a consensus forecast Opinion and Judgmental Methods Forecasting Techniques
  • 15.
    OperationsManagement Forecasting: Modelsand Applications Forecasting Techniques Time series Analysis  A time series is a set of observations of a variable at regular intervals over time.  Assume that what has occurred in the past will continue to occur in the future.  Components of a time series are generally classified as trend T, cyclical C, seasonal S, and random or irregular R.  Time series analysis includes: • moving average • exponential smoothing • linear trend line  Data are tabulated or graphed to show the nature of the time dependence.
  • 16.
    OperationsManagement Forecasting: Modelsand Applications Following are the steps in time series forecasting: 1. Plot historical data to confirm relationship (e.g., linear, exponential, logarithmic etc). 2. Develop a trend equation (T ) to describe the data. 3. Develop a seasonal index (e.g., monthly index values). 4. Project trend into the future (e.g., monthly trend values). 5. Multiply trend values by corresponding seasonal index values. 6. Modify projected values by any knowledge of: • Cyclical business conditions (C) , • Anticipated irregular effects (R) . Time series forecasting procedure Forecasting Techniques
  • 17.
    OperationsManagement  Simple touse  Virtually no cost  Quick and easy to prepare  Data analysis is nonexistent  Easily understandable  Cannot provide high accuracy  Can be a standard for accuracy Naïve Forecasts Forecasting Techniques  The forecast for any period equals the previous period’s actual value.  Demand in current period is used as next period’s forecast Why Naïve Forecasts ? Uh, give me a minute.... We sold 250 wheels last week.... Now, next week we should sell.... 250??? Forecasting: Models and Applications
  • 18.
    OperationsManagement Forecasting Techniques Forecasting: Modelsand Applications Jan 120 Feb 90 Mar 100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90 ORDERS Month Per Month - 120 90 100 75 110 50 75 130 110 90Nov - ?? Forecast Naïve Forecasts Mathematical formula used in Naïve: • Stable time series data F (t ) = A (t -1) • Seasonal variations F (t ) = A (t – n ) • Data with trends F (t ) = A ( t - 1) + (A (t -1) – A(t – 2 ))
  • 19.
    OperationsManagement Three methods fordescribing trend are: 1. Moving average, 2. Hand fitting, and 3. Least squares. A centered moving average is obtained by summing and averaging the values from a given number of periods repetitively, each time deleting the oldest value and adding a new value. Moving averages can smooth out fluctuations in any data, while preserving the general pattern of the. Forecasting Techniques Trend Technique Moving Average Method: Forecasting: Models and Applications
  • 20.
    OperationsManagement The generalized formulafor moving average method is:  Moving average / simple moving average  Weighted moving average  Exponential smoothing Moving Average Method Cont… 𝑴𝑨 = 𝒙 Number of Period Techniques for Averaging – Averaging method – Weights most recent data more strongly – Reacts more to recent changes – Widely used, accurate method Forecasting: Models and Applications Forecasting Techniques
  • 21.
    OperationsManagement A technique thataverages a number of recent actual values, updated as new values become available. MAn = n i = 1  Di n Simple Moving average where n = number of periods in the moving average Di = demand in period i Ft = MAn= n At-n + … At-2 + At-1 Or, Forecasting: Models and Applications Forecasting Techniques
  • 22.
    OperationsManagement 3-month Simple MovingAverage Jan 120 Feb 90 Mar 100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90 Nov - Orders Month Per Month MA3 = 3 i = 1  Di 3 = 90 + 110 + 130 3 = 110 orders for Nov – – – 103.3 88.3 95.0 78.3 78.3 85.0 105.0 110.0 Moving Average Forecasting: Models and Applications Forecasting Techniques
  • 23.
    OperationsManagement Jan 120 Feb 90 Mar100 Apr 75 May 110 June 50 July 75 Aug 130 Sept 110 Oct 90 Nov - Orders Month Per Month – – – – – 99.0 85.0 82.0 88.0 95.0 91.0 Moving Average 5-month Simple Moving Average MA5 = 5 i = 1  Di 5 = 90 + 110 + 130+75+50 5 = 91 orders for Nov Forecasting: Models and Applications Forecasting Techniques
  • 24.
    OperationsManagement 150 – 125 – 100– 75 – 50 – 25 – 0 – | | | | | | | | | | | Jan Feb Mar Apr May June July Aug Sept Oct Nov Actual Orders Month 5-month 3-month Effect of 3-month and 5-month moving average Forecasting: Models and Applications Forecasting Techniques
  • 25.
    OperationsManagement  More recentvalues in a series are given more weight in computing the forecast.  Adjusts moving average method to more closely reflect data fluctuations Weighted Moving Average WMAn = i = 1  Wi Di where Wi = the weight for period i, between 0 and 100 % Wi = 1.00 n Ft = WMAn= wnAt-n + … wn-1At-2 + w1At-1 n Forecasting Techniques Forecasting: Models and Applications
  • 26.
    OperationsManagement MONTH WEIGHT DATA August17% 130 September 33% 110 October 50% 90 WMA3 = 3 i = 1  Wi Di = (0.50)(90) + (0.33)(110) + (0.17)(130) = 103.4 orders November Forecast Forecasting Techniques Forecasting: Models and Applications Example: Weighted Moving Average
  • 27.
    OperationsManagement Forecasting: Modelsand Applications Example: Weighted Moving Average Forecasting Techniques Shipments (in tons) of welded tube by an aluminum producer are shown below: a) Graph the data, and comment on the relationship. b) Compute a 3-year moving average, plot it as a dotted line, and use it to forecast shipments in year 12. c) Using a weight of 3 for the most recent data, 2 for the next, and 1 for the oldest, forecast shipments in year 12. Ref. Operations management, A. Kumar and N. Suresh, New Age, pp. 108-109
  • 28.
    OperationsManagement Solution: Year Shipments 3-ymoving average 1 2 - 2 3 3.7 3 6 6.3 4 10 8.0 5 8 8.3 6 7 9.0 7 12 11.0 8 14 13.3 9 14 15.3 10 18 17.0 11 19 - The MA forecast for year 12 would be that of the latest average, 17.0 tons. The data are plotted as shown: Moving average: = 17.8 tons Example: WMA Cont… Forecasting Techniques Forecasting: Models and Applications
  • 29.
    OperationsManagement The equation usedfor forecast for next period is: where: Ft +1 = forecast for next period Dt = actual demand for present period Ft = previously determined forecast for present period 𝜶 = weighting factor, smoothing constant Exponential Smoothing 𝑭 𝒕+𝟏 = 𝜶𝑫 𝒕 + 𝟏 − 𝜶 𝑭 𝒕 Effect of Smoothing Constant 0.0  1.0 If = 0.20, then Ft +1 = 0.20 Dt + 0.80 Ft If = 0, then Ft +1 = 0 Dt + 1 Ft = Ft Forecast does not reflect recent data If = 1, then Ft +1 = 1 Dt + 0 Ft = Dt ; Forecast based only on most recent data Forecasting Techniques Forecasting: Models and Applications
  • 30.
    OperationsManagement Example: Exponential Smoothing PeriodMonth Demand 1 Jan 37 2 Feb 40 3 Mar 41 4 Apr 37 5 May 45 6 Jun 50 7 Jul 43 8 Aug 47 9 Sep 56 10 Oct 52 11 Nov 55 12 Dec 54 F2 = D1 + (1 - )F1 = (0.30)(37) + (0.70)(37) = 37 F3 = D2 + (1 - )F2 = (0.30)(40) + (0.70)(37) = 37.9 F13 = D12 + (1 - )F12 = (0.30)(54) + (0.70)(50.84) = 51.79 Letting,  =0.30 and so on. Similarly … Forecasting Techniques Forecasting: Models and Applications
  • 31.
    OperationsManagement Forecast, Ft +1 Period Month Demand ( = 0.3) ( = 0.5) 1 Jan 37 – – 2 Feb 40 37.00 37.00 3 Mar 41 37.90 38.50 4 Apr 37 38.83 39.75 5 May 45 38.28 38.37 6 Jun 50 40.29 41.68 7 Jul 43 43.20 45.84 8 Aug 47 43.14 44.42 9 Sep 56 44.30 45.71 10 Oct 52 47.81 50.85 11 Nov 55 49.06 51.42 12 Dec 54 50.84 53.21 13 Jan – 51.79 53.61 Example: Exponential Smoothing Forecasting Techniques Forecasting: Models and Applications
  • 32.
    OperationsManagement 70 – 60 – 50– 40 – 30 – 20 – 10 – 0 – | | | | | | | | | | | | | 1 2 3 4 5 6 7 8 9 10 11 12 13 Actual Orders Month  = 0.50  = 0.30 Forecasting Techniques Forecasting: Models and Applications
  • 33.
  • 34.
    OperationsManagement The generalized equation y= a + bx Where, a = intercept b = slope of the line x = time period y = forecast for demand for period x where n = number of periods = mean of the x values = mean of the y values 𝒃 = 𝒙𝒚 − 𝒏. 𝒙. 𝒚 𝒙 𝟐 − 𝒏 𝒙 𝟐 𝒂 = 𝒚 − 𝒃 𝒙 𝒙 = 𝒙 𝒏 𝒚 = 𝒚 𝒏 Linear Trend Line Forecasting Techniques Forecasting: Models and Applications
  • 35.
    OperationsManagement Example: Linear TrendLine x(Period) y(Demand) xy x2 1 73 37 1 2 40 80 4 3 41 123 9 4 37 148 16 5 45 225 25 6 50 300 36 7 43 301 49 8 47 376 64 9 56 504 81 10 52 520 100 11 55 605 121 12 54 648 144 78 557 3867 650 𝒙 = 𝟕𝟖 𝟏𝟐 = 𝟔. 𝟓 𝒚 = 𝟓𝟓𝟕 𝟏𝟐 = 𝟒𝟔. 𝟒𝟐 𝒃 = 𝒙𝒚−𝒏. 𝒙. 𝒚 𝒙 𝟐−𝒏 𝒙 𝟐 = 1.72 𝒂 = 𝒚 − 𝒃 𝒙 = 𝟒𝟔. 𝟒𝟐 − 𝟏. 𝟕𝟐 × 𝟔. 𝟓 = 𝟑𝟓. 𝟐 Linear trend line y = 35.2 + 1.72x Forecast for period 13, y = 57.56 units Forecasting Techniques Forecasting: Models and Applications
  • 36.
    OperationsManagement  Linear regression •mathematical technique that relates a dependent variable to an independent variable in the form of a linear equation  Correlation • a measure of the strength of the relationship between independent and dependent variables Regression Method The generalized equation, y = a + bx Where, a = intercept, b = slope of the line, x = time period, and y = forecast for demand for period x Linear Regression n = number of periods𝒃 = 𝒙𝒚 − 𝒏. 𝒙. 𝒚 𝒙 𝟐 − 𝒏 𝒙 𝟐 𝒂 = 𝒚 − 𝒃 𝒙 Forecasting Techniques Forecasting: Models and Applications
  • 37.
    OperationsManagement From data, 𝒙 =𝟔. 𝟏𝟐𝟓 X wins Y attendance xy x2 4 36.3 145.2 16 6 40.1 240.6 36 6 41.2 247.2 36 8 53.0 424.0 64 6 44.0 264.0 36 7 45.6 319.2 49 5 39.0 195.0 25 7 47.5 332.5 49 49 346.7 2167.7 311 𝒚 = 𝟒𝟑. 𝟑𝟔 𝒃 = 𝟒. 𝟎𝟔 𝒂 = 𝟏𝟖. 𝟒𝟔 Example: Linear Regression Forecasting Techniques Forecasting: Models and Applications
  • 38.
    OperationsManagement  Correlation, r •Measure of strength of relationship • Varies between -1.00 and +1.00  Coefficient of determination, r2 • Percentage of variation in dependent variable resulting from changes in the independent variable Computing coefficient of correlation: Forecasting Techniques Forecasting: Models and Applications Correlation n xy -  x y [n x2 - ( x)2] [n y2 - ( y)2] r = (8)(2,167.7) - (49)(346.9) [(8)(311) - (49)2] [(8)(15,224.7) - (346.9)2] r = =0.947
  • 39.
    OperationsManagement Multiple Regression Study therelationship of demand to two or more independent variables The relationship is expressed as: y = 0 + 1x1 + 2x2 … + kxk where 0 = the intercept 1, … , k = parameters for the independent variables x1, … , xk = independent variables Forecasting Techniques Forecasting: Models and Applications
  • 40.
    OperationsManagement r2, the coefficient ofdetermination Regression equation coefficients for x1 and x2 Multiple Regression Forecasting Techniques Forecasting: Models and Applications y = 19,094.42 + 3560.99 x1 + .0368 x2 y = 19,094.42 + 3560.99 (7) + .0368 (60,000) = 46,229.35
  • 41.
    OperationsManagement Seasonal Adjustments Forecasting Techniques •Repetitive increase/ decrease in demand • Use seasonal factor to adjust forecast Seasonal factor = Si = Di D year Demand ( in 1000 units) 1 2 3 4 2002 12.686 6.3 17.5 45.0 2003 14.110 7.5 18.2 50.1 2004 15.31 8.1 19.6 53.6 Total 42.029 21.9 55.3 148.7 𝑆1 = 𝐷1 𝐷 = 42.029 148.7 = 0.28 𝑆4 = 55.3 148.7 = 0.37 𝑆3 = 21.9 148.7 = 0.15 𝑆2 = 0.20 SF1 = (S1) (F5) = (0.28)(58.17) = 16.28 SF2 = (S2) (F5) = (0.20)(58.17) = 11.63 SF3 = (S3) (F5) = (0.15)(58.17) = 8.73 SF4 = (S4) (F5) = (0.37)(58.17) = 21.53 y = 40.97 + 4.30x = 40.97 + 4.30(4) = 58.17 For 2005 Forecasting: Models and Applications
  • 42.
  • 43.
    OperationsManagement Click on “Insert”then “Line” Forecasting: Models and Applications Forecasting Techniques
  • 44.
  • 45.
    OperationsManagement Forecasting: Modelsand Applications Forecasting Techniques
  • 46.
    OperationsManagement  No singletechnique works in every situation  Two most important factors o Cost and Accuracy  Other factors include the availability of:  Historical data  Computers  Time needed to gather and analyze the data  Forecast horizon  Forecasts are the basis for many decisions  Work to improve short-term forecasts  Accurate short-term forecasts improve • Profits • Lower inventory levels • Reduce inventory shortages • Improve customer service levels • Enhance forecasting credibility Forecasting: Models and Applications Choosing Forecasting Tech
  • 47.
    OperationsManagement Effect of BadForecasting Forecasting: Models and Applications