Anderson Sweeney Williams Camm Cochran Fry Ohlmann

An Introduction to
Management Science, 15e
Quantitative Approaches to Decision Making

© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Chapter 8: Nonlinear Optimization Models

8.1 – A Production Application – Par, Inc., Revisited

8.2 – Constructing an Index Fund
8.3 – Markowitz Portfolio Model
8.4 – Blending: The Pooling Problem
8.5 – Forecasting Adoption of a New Product

2
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Introduction

Many business processes behave in a nonlinear manner.

• The price of a bond is a nonlinear function of interest rates.
• The price of a stock option is a nonlinear function of the
price of the underlying stock.
• The marginal cost of production often decreases with the
quantity produced.
• The quantity demanded for a product is often a nonlinear
function of the price.

A nonlinear optimization problem is any optimization

problem in which at least one term in the objective function or a
constraint is nonlinear.

3
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Production Application – Par, Inc., Revisited (1 of 4)

Recall that Par, Inc., decided to manufacture standard and

deluxe golf bags. In formulating the linear programming model
for the Par Inc.’s problem, we assumed that it could sell all of
the standard and deluxe bags it could produce. However,
depending on the price of the golf bags, this assumption may
not hold.

An inverse relationship usually exists between price and

demand. As price goes up, the quantity demanded goes down.
Let PS denote the price Par, Inc., charges for each standard
bag and PD denote the price for each deluxe bag.

4
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Production Application – Par, Inc., Revisited (2 of 4)

We can solve the equation, S  2250  15 Ps for Ps

to show how the price of a standard bag is related to the
number of standard bags sold: Ps  150  (1/15) S .

Remember that the profit contribution for producing and selling

S standard bags (revenue – cost) is Ps S  70 S .
Substituting, gives the profit contribution for standard bags:

Ps S  70S
 (150  (1/15) S ) S  70 S

5
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Production Application – Par, Inc., Revisited (3
of 4)

Suppose that the cost to produce each deluxe golf bag is $150.
Using the same logic we used to develop the profit contribution
for standard bags, the profit contribution for deluxe bags is
PD D  150 D  (300  1/15 D) D  150 D  1/ 5 D 2

Total profit contribution is the sum of the profit contribution for

standard bags and the profit contribution for deluxe bags. Thus,
total profit contribution is written as

Total profit contribution  80S  1/15S 2  150 D  1/ 5D 2

6
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Production Application – Par, Inc., Revisited (4 of 4)

Using a computer solution method such as LINGO, we find that

the values of S and D that maximize the profit contribution
function are S = 600 and D = 375.

The corresponding prices are $110 for standard bags and $225
for deluxe bags, and the profit contribution is $52,125.

These values provide the optimal solution for Par, Inc., if all
production constraints are also satisfied.

7
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Constrained Problem (1 of 5)

Unfortunately, Par, Inc., cannot make the profit contribution

associated with the optimal solution to the unconstrained
problem because the constraints defining the feasible region
are violated. For instance, the cutting and dyeing constraint is
7 /10 S  D  630

A production quantity of 600 standard bags and 375 deluxe

bags will require 7/10(600) + 1(375) = 795 hours, which
exceeds the limit of 630 hours by 165 hours.

8
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Constrained Problem (2 of 5)

The feasible region for the original Par, Inc., problem along with
the unconstrained optimal solution point (600, 375) is shown
here:

The unconstrained
optimum of (600,
375) is outside the
feasible region.

9
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Constrained Problem (3 of 5)

The complete mathematical model for the Par, Inc., constrained

nonlinear maximization problem is:

10
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Constrained Problem (4 of 5)

The optimal value of the objective function is $49,920.55. The

optimal solution is to produce 459.7166 standard bags and
308.1984 deluxe bags. In the Slack/Surplus column, the value
of 0 in Constraint 1 means that the optimal solution uses all the
labor hours in the cutting and dyeing department; but the
nonzero values in rows 2–4 indicate that slack hours are
available in the other departments.
Optimal Objective Value = 49920.54655
Variable Value Reduced Cost
S 459.71660 0.00000
D 308.19838 0.00000

Constraint Slack/Surplus Dual Value

1 0.00000 26.7205
2 113.31074 0.00000
3 42.81679 0.00000
4 11.97875 0.00000

11
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
A Constrained Problem (5 of 5)

Here we see three profit contribution contour lines. Each point

on the same contour line is a point of equal profit. Here, the
contour lines show profit contributions of $45,000, $49,920.55,
and $51,500.

For the Par, Inc.,

problem with a
quadratic objective
function, the profit
contours are
ellipses.

12
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Local and Global Optima

A feasible solution is a local optimum if there are no other

feasible solutions with a better objective function value in the
immediate neighborhood.
• For a maximization problem the local optimum
corresponds to a local maximum.
• For a minimization problem the local optimum corresponds
to a local minimum.
• A feasible solution is a global optimum if there are no other
feasible points with a better objective function value in the
feasible region.
• A global optimum is also a local optimum.

13
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Multiple Local Optima

• Nonlinear optimization problems can have multiple local

optimal solutions, in which case we want to find the best local
optimum.
• Nonlinear problems with multiple local optima are difficult to
solve and pose a serious challenge for optimization software.
• In these cases, the software can get “stuck” and terminate at
a local optimum.
• There can be a severe penalty for finding a local optimum
that is not a global optimum.
• Developing algorithms capable of finding the global optimum
is currently a very active research area.

14
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Single Local Maximum

Consider the function f(X, Y) = – X 2 – Y 2.

• A function that is bowl-shaped down is a concave function.
• The maximum value for this particular function is 0 and the
point (0, 0) gives the optimal value of 0.
• Functions such as this one have a single local maximum that
is also a global maximum.
• This type of nonlinear problem is relatively easy to maximize.

15
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Single Local Minimum

Consider the function f(X, Y) = X 2 + Y 2.

• A function that is bowl-shaped up is a convex function.
• The minimum value for this particular function is 0 and the
point (0, 0) gives the optimal value of 0.
• Functions such as this one have a single local minimum that
is also a global minimum.
• This type of nonlinear problem is relatively easy to minimize.

16
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Multiple Local Optima

Consider the function

 X   10 X  X 3  Y 5 e  X   X 1  /3
 Y 1
 5  
2 2 2
2
Y 2 Y 2
f  X ,Y   3 1  X  e
2
e
• The hills and valleys in the
graph show that this
function has several local
maximums and local
minimums.
• There are two local
minimums, one of which is
the the global minimum.
• There are three local
maximums, one of which is
the global maximum.

17
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Dual Values

• Recall that the dual value is the change in the value of the
optimal solution per unit increase in the right-hand side of the
constraint.
• The interpretation of the dual value for nonlinear models is
exactly the same as it is for LPs.
• However, for nonlinear problems the allowable increase and
decrease are not usually reported.
• This is because for typical nonlinear problems the allowable
increase and decrease are zero.
• That is, if you change the right-hand side by even a small
amount, the dual value changes.

18
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Constructing an Index Fund (1 of 5)

Index funds are a very popular investment vehicle in the mutual

fund industry.
• Vanguard 500 Index Fund is the largest mutual fund in the
U.S. with over $70 billion in net assets in 2005.
• An index fund is an example of passive asset management.
• The key idea behind an index fund is to construct a portfolio
of stocks, mutual funds, or other securities that closely
matches the performance of a broad market index such as
the S&P 500.
• Behind the popularity of index funds is research that
basically says “you can’t beat the market.”

19
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Constructing an Index Fund (2 of 5)

Let’s revisit the Hauck Financial Services example from

Chapter 5. Assume that Hauck has a substantial number of
clients who wish to own a mutual fund portfolio with the
characteristic that the portfolio, as a whole, closely matches the
performance of the S&P 500 stock index.

What percentage of the portfolio should be invested in each

mutual fund in order to most closely mimic the performance of
the entire S&P 500 index?

20
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Constructing an Index Fund (3 of 5)
Here are the decision variables:
Planning Scenarios
Mutual Fund Year 1 Year 2 Year 3 Year 4 Year 5

Foreign Stock 10.06 13.12 13.47 45.42 -21.93

Intermediate-Term Bond 17.64 3.25 7.51 -1.33 7.36

Large-Cap Growth 32.41 18.71 33.28 41.46 -23.26

Small-Cap Growth 33.44 19.40 3.85 58.68 -9.02

Small-Cap Value 24.56 25.32 -6.70 5.43 17.31

S&P 500 Return 25.00 20.00 8.00 30.00 -10.00

FS = proportion of portfolio invested in a foreign stock mutual fund

IB = proportion of portfolio invested in an intermediate-term bond fund
LG = proportion of portfolio invested in a large-cap growth fund
LV = proportion of portfolio invested in a large-cap value fund
SG = proportion of portfolio invested in a small-cap growth fund
SV = proportion of portfolio invested in a small-cap value fund

21
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Constructing an Index Fund (4 of 5)

The constraints are:

22
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Constructing an Index Fund (5 of 5)

The optimal value of the objective function is 4.42689,

the sum of the squares of the return deviations.

The portfolio calls for approximately 30% of the funds to

be invested in the foreign stock fund (FS = 0.30334),
36% of the funds to be invested in the large-cap value
fund (LV = 0.36498), 23% of the funds to be invested in
the small-cap growth fund (SG = 0.22655), and 11% of
the funds to be invested in the small-cap value fund (SV
= 0.10513).

23
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Markowitz Portfolio Model

• There is a key tradeoff in most portfolio optimization

models between risk and return.
• The index fund model presented earlier managed the
tradeoff passively.
• The Markowitz mean-variance portfolio model
provides a very convenient way for an investor to
actively trade-off risk versus return.
• We will now demonstrate the Markowitz portfolio
model by extending the previous example.

24
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Markowitz Portfolio Model (1 of 2)

• The portfolio variance is the average of the sum of the

squares of the deviations from the mean value under
each scenario.
• The larger the variance value, the more widely
dispersed the scenario returns are about the average
return value.
• If the portfolio variance were equal to zero, then every
scenario return Ri would be equal.

25
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Markowitz Portfolio Model (2 of 2)

• There are two basic ways to formulate the Markowitz

model:
• (1) Minimize the variance of the portfolio subject to
constraints on the expected return, and
• (2) Maximize the expected return of the portfolio
subject to a constraint on risk.
• We will now demonstrate the first (1) formulation,
assuming the client requires the expected portfolio
return to be at least 10 percent.

26
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Blending: The Pooling Problem (1 of 2)

• Blending problems arise when a manager must decide

how to blend two or more components (resources) to
produce one or more products.
• It is often the case that while transporting or storing
the blending components, the components must share
a pipeline or storage tank.
• In this case, the components are called pooled
components.

27
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Blending: The Pooling Problem (2 of 2)

Two types of decisions arise:

• What should the proportions be for the components
that are to be pooled?
• How much of the pooled and non-pooled
components will be used to make each of the final
products?

28
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (1 of 9)

Grand Strand refinery wants to refine three petroleum

components into regular and premium gasoline in order to
maximize total profit contribution. Components 1 and 2 are
pooled in a single storage tank. Component 3 has its own
storage tank.

The maximum number of gallons available for the three

components are 5000, 10,000, and 10,000, respectively. The
three components cost $2.50, $2.60, and $2.84, respectively.
Regular gasoline sells for $2.90 and premium sells for $3.00. At
least 10,000 gallons of regular gasoline must be produced.

The product specifications for regular and premium gasoline are

shown on the next slide.

29
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (2 of 9)

Product Specifications
• Regular gasolineAt most 30% component 1
At least 40% component 2
At most 20% component 3

• Premium gasoline At least 25% component 1

At most 45% component 2
At least 30% component 3

30
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (3 of 9)

Define the 6 Decision Variables

y1 = gallons of component 2 in the pooling tank

y2 = gallons of component 1 in the pooling tank

x pr = gallons of pooled components 1 and 2 in regular gas
x pp = gallons of pooled components 1 and 2 in premium gas

x3r = gallons of component 3 in regular gasoline

x3 p = gallons of component 3 in premium gasoline

31
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (4 of 9)

Define the Objective Function

Maximize the total contribution to profit (which is revenue from
selling regular and premium gasolines minus cost of buying
components 1, 2, and 3):
Max 2.90( x pr  x3r )  3.00  x pp  x3 p 
 2.50 y1  2.60 y2  2.84  x3r  x3 p 
(Note: x pr  x3r = gallons of regular gasoline sold.

x pp  x3 p = gallons of premium gasoline sold.

x3r  x3 p = gallons of component 3 consumed.)

32
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (5 of 9)

Define the 11 Constraints

Conservation equation:
1) y1  y2  x pr  x pp
Component availability:
2) y1  5, 000
3) y2  10, 000
4) x3r  x3 p  10, 000

Minimum production of regular gasoline:

5) x pr  x3r  10, 000

33
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (6 of 9)

Define the 11 Constraints (continued)

Premium gasoline specifications:

9)  y /  y  y   x  0.25  x  x 
1 1 2 pp pp 3p

10)  y /  y  y   x  0.45  x  x 
2 1 2 pp pp 3p

11) x  0.3  x  x 
3p pp 3p

Non-negativity: x pr , x pp , x3r , x3 p , y1 , y2  0

34
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (7 of 9)

Computer Output
Objective Function Value = 1045000.000

Variable Value Reduced Cost

xpr 8000.000 0.000
x3r 2000.000 0.000
xpp 6000.000 0.000
x3p 2571.429 0.000
ypr 5000.000 0.000
y1 9000.000 0.000

35
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (8 of 9)

Computer Output (continued)

Constraint Slack/Surplus Dual Value
1 0.000 1.412
2 1000.000 0.000
3 5428.571 0.000
4 0.000 -3.061
5 142.857 0.000
6 1142.857 0.000
7 0.000 0.000
8 0.000 -2.197
9 0.000 0.865
10 0.000 0.000
11 0.000 -0.123

36
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Example: Blending - The Pooling Problem (9 of 9)

Solution
Regular Gasoline Premium Gasoline
Component 1 2,857.143 2,142.857
(28.57%) (25.00%)
Component 2 5,142.857 3,857.143
(51.43%) (45.00%)
Component 3 2,000.000 2,571.429
(20.00%) (30.00%)
Total 10,000.000 8,571.429
(100.00%) (100.00%)

37
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Forecasting Adoption of a New Product (1 of 6)

• Forecasting new adoptions (purchases) after a

product introduction is an important marketing
problem.
• We introduce here a forecasting model developed by
Frank Bass.
• Nonlinear programming is used to estimate the
parameters of the Bass forecasting model.

38
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Forecasting Adoption of a New Product (2 of 6)

The Bass model has three parameters that must be

estimated.
• m is the number of people estimated to eventually
adopt a new product
• q is the coefficient of imitation which measures the
likelihood of adoption due to a potential adopter
influenced by someone who has already adopted the
product
• p is the coefficient of imitation which measures the
likelihood of adoption assuming no influence from
someone who has already adopted the product.

39
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Forecasting Adoption of a New Product (3 of 6)

Developing the Forecasting Model

Ft , the forecast of the number of new adopters during
time period t , is
Ft = (likelihood of a new adoption in time period t)
x (number of potential adopters remaining at
the end of time period t – 1)

40
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Forecasting Adoption of a New Product (4 of 6)

Developing the Forecasting Model

• Essentially, the likelihood of a new adoption is the
likelihood of adoption due to innovation plus the likelihood
of adoption due to imitation.
• Let Ct - 1 denote the number of people who have adopted
the product up to time t – 1.
• Hence, Ct - 1 /m is the fraction of the number of people
estimated to adopt the product by time t – 1.
• The likelihood of adoption due to imitation is q(Ct - 1 /m).
• The likelihood of adoption due to innovation and imitation
is p + q(Ct - 1 /m).

41
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Forecasting Adoption of a New Product (5 of 6)

Developing the Forecasting Model

• The number of potential adopters remaining at the
end of time period t  1 is m  Ct 1.
• Hence, the complete forecast model is given by
Ft   p  q  Ct 1 / m    m  Ct 1 

42
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
Forecasting Adoption of a New Product (6 of 6)

Nonlinear Optimization Problem Formulation

N
Min  t
E 2

t 1

Ft   p  q  Ct 1 / m    m  Ct 1  ,
t  1,...., N
Et  Ft  St , t  1,....,
N
where N = number of time periods of data available
Et = forecast error for time period t
St = actual number of adopters (or a multiple of
that number such as sales) in time period t
43
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.
End of Presentation: Chapter 8

44
© 2019 Cengage. All rights reserved. May not be scanned, copied or duplicated, or posted to a publicly accessible website, in whole or in part, except for use as permitted in a
license distributed with a certain product or service or otherwise on a password-protected website or school-approved learning management system for classroom use.