TopRank

TopRank is a “what-if” add-in used for sensitivity analysis. It starts with any spreadsheet
model, where a set of inputs, along with a number of spreadsheet formulas, leads to one or
more outputs. TopRank then performs a sensitivity analysis to see which inputs have the larg-
est effect on a given output. Unlike @RISK, TopRank does not explicitly model uncertainty.

Software Guide
Figure 1.2 illustrates how these add-ins are used throughout the book. Excel doesn’t appear
explicitly in this figure because it is used extensively in all of the chapters.
Developer Add-In Chapter(s) Where Used
Figure 1.2
Software Guide Albright SolverTable
erT
erTable 13, 14

Frontline
Solver 13, 14
Systems, Inc.

@RISK 15–16

PrecisionT
PrecisionTree 6

Palisade Corp. StatT

StatTools 2, 3, 7–12, 17, 19–20

© Cengage Learning
NeuralT
NeuralTools 17

BigPicture 13–16

With Excel and the add-ins available with the book, you have a wealth of software at your
disposal. The examples and step-by-step instructions throughout the book will help you become
a power user of this software. Admittedly, this takes plenty of practice and a willingness to exper
exper-
iment, but it is certainly within your grasp. When you are finished, it is very possible that you
will rate “improved software skills” as the most valuable thing you have learned from the book.

1-3 MODELING AND MODELS

The term model has already appeared several times in this chapter. Models and the modeling
process are key elements throughout the book, so we explain them here in more detail.6
A model is an abstraction of a real problem. A model tries to capture the essence and
key features of the problem without getting bogged down in relatively unimportant details.
There are different types of models, and depending on an analyst’s preferences and skills,
each can be a valuable aid in solving a real problem. We briefly describe three types of
models here: graphical models, algebraic models, and spreadsheet models.

1-3a Graphical Models

Graphical models are probably the most intuitive and least quantitative type of model. They
attempt to portray graphically how different elements of a problem are related—what affects

6
Management scientists tend to use the terms model and modeling more than statisticians. However, many tradi-
tional statistics topics such as regression analysis and forecasting are definitely applications of modeling.

10 Chapter 1 Introduction to Business Analytics

Copyright 2017 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. WCN 02-200-203
 what. A fairly simple graphical model for an ordering decision appears in Figure 1.3. (It was
created with Palisade’s BigPicture add-in.)

Figure 1.3 Parameters of

Unit Price
Graphical Model Demand Funcon
of an Ordering
Decision

Demand

Unit Cost to
Costt R
Revenue
Produce

© Cengage Learning
Maximize
Profit

This diagram indicates fairly intuitively what affects what. It does not provide enough
quantitative details to “solve” the company’s problem, but this is usually not the purpose
of a graphical model. Instead, its purpose is usually to show the important elements of a
problem and how they are related. For complex problems, this can be very enlightening
information for management.

1-3b Algebraic Models

Algebraic models are at the opposite end of the spectrum. Using algebraic equations and
inequalities, they specify a set of relationships in a very precise way. Their preciseness and
lack of ambiguity are very appealing to people with a mathematical background. In addi-
tion, algebraic models can usually be stated concisely and with great generality.
A typical example is the “product mix” problem in Chapter 13. A company can make
several products, each of which contributes a certain amount to profit and consumes certain
amounts of several scarce resources. The problem is to select the product mix that maxi-
mizes profit subject to the limited availability of the resources. All product mix problems
can be stated algebraically as follows:

Algebraic Product Mix Model

max a pj xj
n
(1.1)
j=1

b ect to a aiji xj ≤ bi, 1 ≤ i ≤ m

n
subj
bj (1.2)
j=1

0 ≤ xj ≤ uj, 1 ≤ j ≤ n (1.3)

1-3 Modeling and Models 11

Copyright 2017 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. WCN 02-200-203
 Here xj is the amount of product j produced, uj is an upper limit on the amount of
product j that can be produced, pj is the unit profit margin for product j, aiji is the amount
of resource i consumed by each unit of product j, bi is the amount of resource i available,
n is the number of products, and m is the number of scarce resources. This algebraic
model states very concisely that we should maximize total profit [Expression (1.1)],
subject to consuming no more of each resource than is available [Inequality (1.2)], and
all production quantities should be between 0 and their upper limits [Inequality (1.3)].
Algebraic models appeal to mathematically trained analysts. They are concise, they
spell out exactly which data are required (the values of the uj’s, the pj’s, the aiji ’s, and the
bj’s would need to be estimated from company data), they scale well (a problem with 500
products and 100 resource constraints is just as easy to state as one with only five products
and three resource constraints), and many software packages accept algebraic models in
essentially the same form as shown here, so that no “translation” is required. Indeed, alge-
braic models were the preferred type of model for years—and still are by many analysts.
Their main drawback is that they require an ability to work with abstract mathematical
symbols. Some people have this ability, but many perfectly intelligent people do not.

1-3c Spreadsheet Models

An alternative to algebraic modeling is spreadsheet modeling. Instead of relating various
quantities with algebraic equations and inequalities, they are related in a spreadsheet with
cell formulas. In our experience, this process is much more intuitive to most people. One
of the primary reasons for this is the instant feedback available from spreadsheets. If you
enter a formula incorrectly, it is often immediately obvious (from error messages or unreal-
istic numbers) that you have made an error, which you can then go back and fix. Algebraic
models provide no such immediate feedback.
A specific comparison might help at this point. You already saw a general algebraic
model of the product mix problem. Figure 1.4, taken from Chapter 13, illustrates a spread-
sheet model for a specific example of this problem. The spreadsheet model should be fairly
self-explanatory. All quantities in shaded cells (other than in rows 16 and 25) are inputs to
the model, the quantities in row 16 are the decision variables (they correspond to the xj’s in
the algebraic model), and all other quantities are created through appropriate Excel formu-
las. To indicate constraints, inequality signs have been entered as labels in appropriate cells.
Although a well-designed and well-documented spreadsheet model such as the one in
Figure 1.4 is undoubtedly more intuitive for most people than its algebraic counterpart, the
art of developing good spreadsheet models is not easy. Obviously, they must be correct.
The formulas relating the various quantities must have the correct syntax, the correct cell
references, and the correct logic. This can be quite a challenge in complex models.
However, correctness is not enough. If spreadsheet models are to be used in the busi-
ness world, they must also be well designed and well documented. Otherwise, no one
other than you (and maybe not even you after a few weeks have passed) will be able to
understand what your models do or how they work. The strength of spreadsheets is their
flexibility—you are limited only by your imagination. However, this flexibility can be a
liability in spreadsheet modeling unless you design your models carefully.
Note the clear design in Figure 1.4. Most of the inputs are grouped at the top of the
spreadsheet. All of the financial calculations are done at the bottom. When there are con-
straints, the two sides of the constraints are placed next to each other (as in the range
B21:D22). Colored backgrounds (which appear on a computer monitor but not in the book)
are used for added clarity, and descriptive labels are used liberally. Excel itself imposes
none of these “rules,” but you should impose them on yourself.
We have made a conscious effort to establish good habits for you to follow throughout
the book. We have designed our spreadsheet models so that they are as clear as possible.

12 Chapter 1 Introduction to Business Analytics

Copyright 2017 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. WCN 02-200-203
Figure 1.4 Product Mix Model

A B C D E F G
1 Assembling and tesng computers Range names used:
2 Hours_availablee =
=Model!$D$21:$D$22
3 Cost per labor hour assemblingg $11
$ Hours_used =Model!$B$21:$B$22
4 Cost per labor hour tes
ngg $
$15 Maximum_saless ==Model!$B$18:$C$18
5 Number_to_producee ==Model!$B$16:$C$16
6 Inputs for assembling and tes
ng a computer Total_profit =Model!$D$25
7 Basic XP
8 Labor hours for assembly 5 6
9 Labor hours for testing 1 2
10 Cost of component parts $150 $225
11 Sellingg price $300 $450
12 Unit margin $80 $129
13
14 Assembling, tes
ng plan (# of computers)
15 Basic XP
16 Number to produce 560 1200
17 <= <=
18 Maximum sales 600 1200
19
20 Constraints (hours per month) Hours used Hours available
21 Labor availability for assembling 100000 <
<= 10000
22 Labor availability for tes
ng 2960
0 <<= 3000
23
24 Net profit ($ this month) Basic XP Total
25 $44,800 $154,800 $199,600

This does not mean that you have to copy everything we do—everyone tends to develop
their own spreadsheet style—but our models should give you something to emulate. Just
remember that in the business world, you typically start with a blank spreadsheet. It is
then up to you to develop a model that is not only correct but is also intelligible to you
and others. This takes a lot of practice and a lot of editing, but it is a skill well worth
developing.

1-3d A Seven-Step Modeling Process

Most of the modeling you will do in this book is only part of an overall modeling process
typically done in the business world. We portray it as a seven-step process, as discussed
here. Admittedly, not all problems require all seven steps. For example, the analysis of
survey data might entail primarily steps 2 (data analysis) and 5 (decision making) of the
process, without the formal model building discussed in steps 3 and 4.

The Modeling Process

1. Define the problem. Typically, a company does not develop a model unless it believes
it has a problem. Therefore, the modeling process really begins by identifying an
underlying problem. Perhaps the company is losing money, perhaps its market share
is declining, or perhaps its customers are waiting too long for service. Any number
of problems might be evident. However, as several people have warned [see Miser
(1993) and Volkema (1995) for examples], this step is not always as straightforward as

1-3 Modeling and Models 13

Copyright 2017 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. WCN 02-200-203
 it might appear. The company must be sure that it has identified the correct problem
before it spends time, effort, and money trying to solve it.
For example, Miser cites the experience of an analyst who was hired by the
military to investigate overly long turnaround times between fighter planes landing
and taking off again to rejoin the battle. The military was convinced that the prob-
lem was caused by inefficient ground crews; if they were faster, turnaround times
would decrease. The analyst nearly accepted this statement of the problem and was
about to do classical time-and-motion studies on the ground crew to pinpoint the
sources of their inefficiency. However, by snooping around, he found that the prob-
lem obviously lay elsewhere. The trucks that refueled the planes were frequently
late, which in turn was due to the inefficient way they were refilled from storage
tanks at another location. Once this latter problem was solved—and its solution
was embarrassingly simple—the turnaround times decreased to an acceptable level
without any changes on the part of the ground crews. If the analyst had accepted the
military’s statement of the problem, the real problem might never have been located
or solved.
2. Collect and summarize data. This crucial step in the process is often the most
tedious. All organizations keep track of various data on their operations, but these
data are often not in the form an analyst requires. They are also typically scattered
in different places throughout the organization, in all kinds of different formats.
Therefore, one of the first jobs of an analyst is to gather exactly the right data and
summarize the data appropriately—as discussed in detail in Chapters 2 and 3—for
use in the model. Collecting the data typically requires asking questions of key peo-
ple (such as the accountants) throughout the organization, studying existing data-
bases, and performing time-consuming observational studies of the organization’s
processes. In short, it entails a lot of legwork. Fortunately, many companies have
understood the need for good clean data and have spent large amounts of time and
money to build data warehouses for quantitative analysis.
3. Develop a model. This is the step we emphasize, especially in the latter chapters
of the book. The form of the model varies from one situation to another. It could be
a graphical model, an algebraic model, or a spreadsheet model. The key is that the
model must capture the important elements of the business problem in such a way
that it is understandable by all parties involved. This latter requirement is why we
favor spreadsheet models, especially when they are well designed and well docu-
mented.
4. Verify the model. Here the analyst tries to determine whether the model developed
in the previous step is an accurate representation of reality. A first step in determin-
ing how well the model fits reality is to check whether the model is valid for the
current situation. This verification can take several forms. For example, the analyst
could use the model with the company’s current values of the input parameters. If the
model’s outputs are then in line with the outputs currently observed by the company,
the analyst has at least shown that the model can duplicate the current situation.
A second way to verify a model is to enter a number of input parameters (even
if they are not the company’s current inputs) and see whether the outputs from the
model are reasonable. One common approach is to use extreme values of the inputs
to see whether the outputs behave as they should. If they do, this is another piece of
evidence that the model is reasonable.
If certain inputs are entered in the model and the model’s outputs are not as
expected, there could be two causes. First, the model could be a poor representation of
reality. In this case it is up to the analyst to refine the model so that it is more realistic.

14 Chapter 1 Introduction to Business Analytics

Copyright 2017 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. WCN 02-200-203
 The second possible cause is that the model is fine but our intuition is not very good.
In this case the fault lies with us, not the model. The fact that outcomes sometimes
defy intuition is an important reason why models are important. These models prove
that our ability to predict outcomes in complex environments is often not very good.
5. Select one or more suitable decisions. Many, but not all, models are decision
models. For any specific decisions, the model indicates the amount of profit
obtained, the amount of cost incurred, the level of risk, and so on. If the model is
working correctly, as discussed in step 4, then it can be used to see which decisions
produce the best outputs.
6. Present the results to the organization. In a classroom setting you are typically
finished when you have developed a model that correctly solves a particular prob-
lem. In the business world a correct model, even a useful one, does not always
suffice. An analyst typically has to “sell” the model to management. Unfortunately,
the people in management are sometimes not as well trained in quantitative methods
as the analyst, so they are not always inclined to trust complex models.
There are two ways to mitigate this problem. First, it is helpful to include
relevant people throughout the company in the modeling process—from beginning
to end—so that everyone has an understanding of the model and feels an ownership
of it. Second, it helps to use a spreadsheet model whenever possible, especially
if it is designed and documented properly. Almost everyone in today’s business
world is comfortable with spreadsheets, so spreadsheet models are more likely to
be accepted.
7. Implement the model and update it over time. Again, there is a big difference
between a classroom situation and a business situation. When you turn in a classroom
assignment, you are typically finished with that assignment and can await the next one.
In contrast, an analyst who develops a model for a company usually cannot pack up his
bags and leave. If the model is accepted by management, the company will then need to
implement it company-wide. This can be very time consuming and politically difficult,
especially if the model’s suggestions represent a significant change from the past. At
the very least, employees must be trained how to use the model on a day-to-day basis.
In addition, the model will probably have to be updated over time, either
because of changing conditions or because the company sees more potential uses
for the model as it gains experience using it. This presents one of the greatest chal-
lenges for a model developer, namely, the ability to develop a model that can be
modified as the need arises.

1-4 CONCLUSION
In this chapter we have tried to convince you that the skills in this book are important for
you to know as you enter the business world. The methods we discuss are no longer the sole
province of the “quant jocks.” By having a computer that is loaded with powerful software,
you incur a responsibility to use this software to analyze business problems effectively. We
have described the types of problems you will learn to analyze in this book, along with the
software you will use to analyze them. We also discussed the modeling process, a theme
that runs throughout this book. Now it is time for you to get started!

1-4 Conclusion 15
Copyright 2017 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. WCN 02-200-203
 CASE 1.1 E NTERTAINMENT ON A C RUISE S HIP

C ruise ship traveling has become big business.

Many cruise lines are now competing for
customers of all age groups and socioeconomic
performances.7 Although this entertainment was free
to all of the passengers, much of it had embarrassingly
low attendance. The nightly show band and musical
levels. They offer all types of cruises, from relatively combos, who were contracted to play nightly
inexpensive 3- to 4-day cruises in the Caribbean, until midnight, often had less than a half-dozen
to 12- to 15-day cruises in the Mediterranean, to people in the audience—sometimes literally none.
several-month around-the-world cruises. Cruises The professional singers, dancers, and comedians
have several features that attract customers, many of attracted larger audiences, but there were still plenty
whom book six months or more in advance: (1) they of empty seats. In spite of this, the cruise staff posted
offer a relaxing, everything-done-for-you way a weekly schedule, and they stuck to it regardless of
to travel; (2) they serve food that is plentiful, attendance. In a short-term financial sense, it didn’t
usually excellent, and included in the price of the make much difference. The performers got paid the
cruise; (3) they stop at a number of interesting same whether anyone was in the audience or not,
ports and offer travelers a way to see the world; the passengers had already paid (indirectly) for the
and (4) they provide a wide variety of entertainment, entertainment as part of the cost of the cruise, and
particularly in the evening. the only possible opportunity cost to the cruise
This last feature, the entertainment, presents line (in the short run) was the loss of liquor sales
a difficult problem for a ship’s staff. A typical cruise from the lack of passengers in the entertainment
might have well over 1000 passengers, including lounges. The morale of the entertainers was not
elderly singles and couples, middle-aged people great—entertainers love packed houses—but they
with or without children, and young people, often usually argued, philosophically, that their hours were
honeymooners. These various types of passengers relatively short and they were still getting paid to see
have varied tastes in terms of their after-dinner the world.
preferences in entertainment. Some want traditional If you were in charge of entertainment on
dance music, some want comedians, some want rock this ship, how would you describe the problem
music, some want movies, some want to go back to with entertainment: Is it a problem with deadbeat
their cabins and read, and so on. Obviously, cruise passengers, low-quality entertainment, or a
entertainment directors want to provide the variety mismatch between the entertainment offered and
of entertainment their customers desire—within the entertainment desired? How might you try to
a reasonable budget—because satisfied customers solve the problem? What constraints might you have
tend to be repeat customers. The question is how to to work within? Would you keep a strict schedule
provide the right mix of entertainment. such as the one followed by this cruise director, or
On a cruise one of the authors and his wife took would you play it more by ear? Would you gather
a few years ago, the entertainment was of high quality data to help solve the problem? What data would
and there was plenty of variety. A seven-piece show you gather? How much would financial considerations
band played dance music nightly in the largest lounge, dictate your decisions? Would they be long-term or
two other small musical combos played nightly at two short-term considerations?
smaller lounges, a pianist played nightly at a piano
bar in an intimate lounge, a group of professional
singers and dancers played Broadway-type shows 7
There was also a moderately large onboard casino, but it tended to
about twice weekly, and various professional attract the same people every night, and it was always closed when
singers and comedians played occasional single-night the ship was in port.

16 Chapter 1 Introduction to Business Analytics

Copyright 2017 Cengage Learning. All Rights Reserved. May not be copied, scanned, or duplicated, in whole or in part. WCN 02-200-203