Synopses & Reviews
“A manager who wants to learn the underlying techniques and their applicability is bound to tutorials from a data scientist with good communication skills. This book gives managers the opportunity to learn the concepts by themselves, and thus, it should be on a bookshelf of everyone who leads and manages analytics efforts.”
–Diego Klabjan, Professor of Industrial Engineering and Management Sciences, Director of Master of Science in Analytics Program, Northwestern University
“Watson and Nelson help to bridge the gap between the marketing hype and the technical details, making it easier to evaluate analytics-based solutions and better understand their potential.”
–Irv Lustig, Ph.D., Manager, Optimization and Mathematical Software, Business Analytics and Math Science, IBM Research at IBM
Analytics and Big Data Demystified
The up-to-the-minute introduction for every manager
• Everything you need to know to get results!
• Concepts, applications, tools, techniques, and pitfalls to avoid
• How to derive more value from tools and data you already own
Want to start leveraging analytics and Big Data for profit? Managerial Analytics is your ideal first resource. Whatever your industry or management role, this up-to-date guide will help you get started fast, get started right, and quickly start driving value.
Right now, analytics is helping organizations do everything from saving money to saving lives. Chances are, your organization has enormous opportunities to derive value through analytics—if you apply it properly.
Managerial Analytics will show you how. This book is for every manager who knows they can benefit from analytics, but doesn’t know where to start…every consultant and software provider who wants to deliver better results to clients…every professional tasked with evaluating analytics products or vendors.
Using practical examples, the authors demystify each form of analytics: descriptive analytics for presenting and visualizing data; predictive analytics for recognizing trends and relationships; and prescriptive analytics for optimizing decisions based on what you know and expect.
For each, they introduce today’s best tools and techniques, offering just enough technical detail to help you make the best possible choices. You’ll learn how modern analytics differs from older techniques; what kind of questions you can now answer for the first time; and how to extend the power of analytics throughout your entire organization.
• What analytics is, what it isn’t…
…and what it really means to “compete on analytics”
• Developing the right mindset for the successful analytics project
Thinking clearly about your problem and your data
• Leveraging the tools and data you already have
Surprising opportunities to gain value from existing resources
• Overcoming pitfalls that lead to the wrong answers
Getting the right samples, avoiding “confirmation bias,” and more
Synopsis
The field of analytics is rapidly evolving, making it difficult for professionals and students to keep up the most current and effective applications. Managerial Analytics will help readers sort through all these new options and identify the appropriate solution. In this reference, authors Watson, Nelson and Cacioppi accurately define and identify the components of analytics and big data, giving readers the knowledge needed to effectively assess new aspects and applications. Building on this foundation, they review tools and solutions, identify the offerings best aligned to one’s requirements, and show how to tailor analytics applications to an organization’s specific needs. Drawing on extensive experience implementing, planning, and researching advanced analytics for business, the authors clearly explain all this, and more:
- What analytics is and isn’t: great examples of successful usage – and other examples where the term is being degraded into meaninglessness
- The difference between using analytics and “competing on analytics”
- How to get started with big data, by analyzing the most relevant data
- Components of analytics systems, from databases and Excel to BI systems and beyond
- Anticipating and overcoming “confirmation bias” and other pitfalls
- Understanding predictive analytics and getting the high-quality random samples necessary
- Applying game theory, Efficient Frontier, benchmarking, and revenue management models
- Implementing optimization at the small and large scale, and using it to make “automatic decisions”
About the Author
Michael Watson is currently a partner at Opex Analytics and an Adjunct Professor at Northwestern University. At Opex Analytics he helps bring new analytics solutions to companies. Prior to Opex Analytics, he was a manager at IBM in the ILOG supply chain and optimization group. At Northwestern, he teaches a program on operations management and managerial analytics in the McCormick School of Engineering’s Masters in Engineering Management (MEM). He teaches optimization in Northwestern’s Master of Science in Analytics program. He holds an M.S. and Ph.D. from Northwestern University in Industrial Engineering and Management Sciences.
Derek Nelson is currently a senior principal at OPS Rules and an Adjunct Professor at Northwestern University. At OPS Rules, Derek leverages analytics to help companies improve operational performance. Prior to OPS Rules, Derek held consulting, product management, and technical sales roles in optimization and supply chain software for LogicTools, ILOG, and IBM. At Northwestern, Derek has taught service operations management to undergraduates in the Industrial Engineering and Management Sciences department and will soon be teaching in the Master in Engineering Management (MEM) program. Derek holds an M.S. in Operations Research from Cornell University.
Table of Contents
Preface xv
Part I Overview 1
Chapter 1 What Is Managerial Analytics? 3
Chapter 2 What Is Driving the Analytics Movement? 23
Chapter 3 The Analytics Mindset 35
Part II Analytics Toolset 63
Chapter 4 Machine Learning 65
Chapter 5 Descriptive Analytics 93
Chapter 6 Predictive Analytics 139
Chapter 7 Case Study: Moneyball and Optimization 155
Chapter 8 Prescriptive Analytics (aka Optimization) 163
Part III Conclusion 199
Chapter 9 Revenue Management 201
Chapter 10 Final Tips for Implementing Analytics 211
Nontraditional Bibliography and Further Reading 215
Endnotes 221
Index 227