4CHANGE PROPOSALPRESENTATIONFORFACULTY REVIEWCapston

4
CHANGE PROPOSALPRESENTATIONFORFACULTY
REVIEW
Capstone Project Change Proposal Presentation for Faculty
Review and Feedback
Name
Name of the institution
Date
Running head: ASSIGNMENT TITLE HERE
1Running head: CHANGE PROPOSAL PRESENTATION FOR
FACULTY REVIEW
Intervention
The capstone change proposal is effects of disproportionate
nurse to patient staffing ratios on the quality of patient care.
Patients can be exposed to several safety issues if proper care is
not given to them. These problems include falls, hospital-
acquired infection due to poor hand hygiene by the healthcare
workers, medication administration errors, poor health
education to the patients, and negligence in attending to the
spiritual needs of the patients. Interventions includes presenting
the safety concerns to the management team of the facility to
enable them to hire more nurses to deliver adequate care to the

patients. In-service training of the nurses on fall prevention,
proper application of fall precautions and identification of
patients who are at risk of falls are another important
intervention. Proper hand hygiene is an intervention that will
prevent hospital-acquired infections and nurses should form the
culture of doing it (Sands, & Aunger, 2020). Medication errors
can lead to complications or death of patients. Nurses should
check the medications properly and identify the patients before
administration of the medications.
Evidence Based Literature
The articles reviewed have different research aims and
questions, but they are all centered into the idea of the effects
of nurse-to-patient ratios on patient outcomes. The research
questions of these articles are divided into three categories:
definition of nursing staffing, effects of nursing-to-patient ratio
on patient outcomes and nursing characteristics that hinders the
delivery of care. The study by (Cho et al., 2020), defines the
term nursing staffing in terms of the nursing care needs of the
patients.
Nurses are essential in the provision of quality care in acute
units, and their staffing levels have an impact on patient
outcomes. (Cho et al., 2015), examine the link between nursing
staffing and patient outcomes, specifically the mortality rate.
Comparing to (Driscoll et al., 2018) and (Shin et al., 2018), the
articles examine the effects of nursing staffing ratios on the
patient outcomes in acute specialist units. Besides, (Needleman,
2016) reviews the studies that examine the effects of nursing
skill mix on the patient outcomes such as patient ratings of
hospitals, mortality, adverse health outcomes, and nurse burnout
and dissatisfaction.
Some of the factors such as nursing skills, staffing methods, and
working environment affects the nursing staffing ratio, which
hinders the quality of care. The article by (Bridges et al., 2019),
explores the relationship between nursing staffing skills and the
quality and quantity of their interactions with patients in
hospital wards. (Olley et al., 2019) evaluate research on nursing

staffing methods and their implication to patient outcomes in
acute hospitals. (Song et al., 2020) aim to find out the
association of the missing essential care tasks in nursing homes
and the work environment.
Objectives of the Study
The aim of the project is to determine the condition under which
the impact of hospital nurse staffing is associated with patient
outcome. To determine the incidence of fall associated with
hospital and unit staffing. Falls-prevention programs needs to
be carefully targeted to patients at greatest risk in other to
achieve cost saving (Spetz et al., 2015). To determine the work
environment and staffing effect on nurses. To develop evidence-
based intervention to reduce the rise of hospital-acquired
infections in the hospital.
Resources Needed
Resources needed in the capstone change proposal included
communication, finance, leadership and management, new
policies and regulations, and hospital libraries.
Good communication between nurses and patients is critical for
personalized nursingcare of each patient (Dithole et al., 2017).
The management team needs update on the project by telephone
calls, email, text messages, project introduction of the seminar
that requires the use of computers and projectors. Funds are
needed to purchase supplies such as water, soaps, fal ls
prevention equipment, computers, projectors, face masks, hand
gloves, sanitizers, and disinfectants. Leaders and managers have
the power to influence the policies that will favor my project’s
implementation, so they are especially useful resources.
Anticipated Measurable Outcomes
The measurable outcomes of the capstone change proposal are
reduction of nurse’s burnout. Nurse burnout is characterized by
the reduction of energy which can negatively impact on work
output, and lack of motivation in a nurse (Mudallal et al.,
2017). Improving safety outcomes and increasing the quality of
life of the patients. Implementing adequate nurse staffing ratios
will help in promoting quality care, which will reduce the rate

of hospital readmissions or length of stays in intensive care
units, which are often expensive.
How the Intervention will be Evaluated
Evaluation of the intervention will be done through random
selection of patients admitted in acute section of the facility.
Assessment of fall rate and fall prevention practice before and
after the implementation of the project, will enable to determine
if progress is made. Checking the infection control records to
determine the number of cases after the implementation of the
project will determine how well hand hygiene practices are
carried out by the nurses, and other health workers. Checking
admission records to obtain information about the number of
readmissions is another way of evaluating the intervention.
Interviewing the randomly selected patients on general
satisfaction of nursing care is one way to evaluating the
intervention. Errors of nurses can result to safety concerns in
the facility (Palteki et al., 2020). Assessment of the nurse to
patient ratios will show if the management hires more nurses to
take care of the patients.
References
Mudallal, R. H., Othman, W. M., & Al Hassan, N. F. (2017).
Nurses' burnout: The influence of leader empowering behaviors,
work conditions, and demographic traits. Inquiry: A Journal of
Medical Care Organization, Provision, and Financing, 54,
46958017724944. https://doi.org/10.1177/0046958017724944
Dithole, K. S., Thupayagale-Tshweneagae, G., Akpor, O. A., &
Moleki, M. M. (2017). Communication skills intervention:
promoting effective communication between nurses and
mechanically ventilated patients. BMC Nursing, 16, 1–6.
https://doi-org.lopes.idm.oclc.org/10.1186/s12912-017-0268-5
Sands, M., & Aunger, R. (2020). Determinants of hand hygiene
compliance among nurses in US hospitals: A formative research
study. Plos One, 15(4), 1–29. https://doi-
org.lopes.idm.oclc.org/10.1371/journal.pone.0230573
Palteki, T., Sur, H., Yazıcı, G., Þimþek, E. E., & Baktýr, Y.
(2020). Evaluation of the patients’ attitudes and behaviors

concerning patient safety. Southern clinics of Istanbul
Eurasia, 31(1), 69–74. https://doi-
org.lopes.idm.oclc.org/10.14744/scie.2020.80299
Cho, E., Sloane, D. M., Kim, E.-Y., Kim, S., Choi, M., Yoo, I.
Y., Lee, H. S., & Aiken, L. H. (2015). Effects of nurse staffing,
work environments, and education on patient mortality: An
observational study. International Journal of Nursing
Studies, 52(2), 535–542.
https://doi.org/10.1016/j.ijnurstu.2014.08.006
Cho, S.-H., Lee, J.-Y., Hong, K. J., Yoon, H.-J., Sim, W.-H.,
Kim, M.-S., & Huh, I. (2020). Determining nurse staffing by
classifying patients based on their nursing care needs. Journal
of Korean Academy of Nursing Administration, 26(1), 42.
https://doi.org/10.11111/jkana.2020.26.1.42
Driscoll, A., Grant, M. J., Carroll, D., Dalton, S., Deaton, C.,
Jones, I., Lehwaldt, D., McKee, G., Munyombwe, T., & Astin,
F. (2018). The effect of nurse-to-patient ratios on nurse-
sensitive patient outcomes in acute specialist units: A
systematic review and meta-analysis. European Journal of
Cardiovascular Nursing: Journal of the Working Group on
Cardiovascular Nursing of the European Society of
Cardiology, 17(1), 6–22.
https://doi.org/10.1177/1474515117721561
Needleman, J. (2016). Nursing skill mix and patient
outcomes. BMJ Quality & Safety, 26(7), 525–528.
https://doi.org/10.1136/bmjqs-2016-006197
Olley, R., Edwards, I., Avery, M., & Cooper, H. (2019).
Systematic review of the evidence related to mandated nurse
staffing ratios in acute hospitals. Australian Health
Review, 43(3), 288. https://doi.org/10.1071/ah16252
Shin, S., Park, J.-H., & Bae, S.-H. (2018). Nurse staffing and
nurse outcomes: A systematic review and meta-
analysis. Nursing Outlook, 66(3), 273–282.
https://doi.org/10.1016/j.outlook.2017.12.002
Song, Y., Hoben, M., Norton, P., & Estabrooks, C. A. (2020).
Association of Work Environment with Missed and Rushed Care

Tasks Among Care Aides in Nursing Homes. JAMA Network
Open, 3(1), e1920092.
https://doi.org/10.1001/jamanetworkopen.2019.20092
Spetz, J., Brown, D. S., & Aydin, C. (2015). The economics of
preventing hospital falls: Demonstrating ROI through a simple
model. The Journal of Nursing Administration, 45(1), 50–57.
https://doi.org/10.1097/NNA.0000000000000154
%25
%22
%2
SafeAssign Originality Report
Summer 2020 - Business Intelligence (ITS-531-06) - First … •
Week 4 Assignment
%49Total Score: High riskSruthi Dhadvai
Submission UUID: 24de29e0-b2f4-c86f-3c3c-1670aa7508bb
Total Number of Rep…
1
Highest Match
49 %
WK4Assignment.docx
Average Match
49 %
Submitted on

05/30/20
05:25 PM EDT
Average Word Count
1,049
Highest: WK4Assignment.…
%49Attachment 1
Internet (4)
kdnu… kdnu… papers
kupdf
Institutional database (8)
Stud… Stud… Stud…
Stud… Stud… Stud…
Stud… Stud…
Global database (1)
Stud…
Top sources (3)
Excluded sources (0)
View Originality Report - Old Design
Word Count: 1,049

WK4Assignment.docx
5 6 10
7
8 2 4
11 3 1
9 13
12
5 kdnu… 8 Stud… 6 kdnu…
Running Head: ASSIGNMENT 4 1
ASSIGNMENT 4 2
Assignment #4
Sruthi Dhadvai
University of the Cumberlands
Business Intelligence ITS 531 – 06 Summer 2020 First Bi-Term
Q1: Data mining is considered to be a procedure which depends
on algorithms in analyzing as well as extracting information
which
is useful from given data. Data mining can be utilized in
automatically discovering patterns that are hidden in addition to

relations
in information, as well as predicting results from data sets that
are large. Text mining is identified as a set of procedure
needed to convert text documents that are unstructured or
resources to structured information which is valuable.
Sentiment
analysis extracts texts from social networks, online reviews,
emails, interactions on call center in addition to various sources
of
information to identifying threads that are common which point
negative or positive feelings on a clients’ part. Sentiment
analysis is
known to be the study of information which is subjective in a
given expression, such as appraisals, opinions, and attitudes in
addition to emotion in regard to a certain topic, entity or
person. Expressions are either categorized as negative, neutral
or positive
(Allahyari, et.al, 2017). Q2: Text mining is used to explore as
well as analyze huge sums of text data which unstructured
assisted by a
software which is capable of identifying patterns, concepts,
keywords, topics as well as additional attributes within the data.
This
process is also referred to as text analytics; however, several
individuals have a distinction drawn in between both terms.
From that
perspective, text analytics is considered to be an applicati on
which is enabled through utilization of techniques of text
mining in
sorting through sets of data (Kong and Gerstein, 2018).
Applications of text mining include risk management this means
integrating
as well as adopting software of risk management which is
powered through text mining techniques like SAS text miner
help

enterprises in staying updated generally with trends that are
current within the enterprise market. Another application is the
customer service; techniques in text mining are getting
enhanced importance within the customer care field. Q3: Text
analytics is
considered to help during the process of building additional
structure in addition to metadata across a text which was
initially
unstructured. Through the addition of extra structure, it
becomes possible in deriving more value. Inducing structure
basically
means first having structure imposed unto the data, thereafter
have the structured data mined. Several ways of inducing
structure
into data include isolation of key words; determining the key
topics basically meaning the text has to be classified according
to the
matter of subject in addition to measuring the sentiment this
means having the tone gauged. Q4: NLP basically plays the role
of
leveraging the tireless computer’s speed into applying analysis
which is human like into text. Technologies that are new such
as text
embedding basically convert words as well as phrases into
vectors that are mathematical which make it possible for easy
comparing on how both phrases are similar. In simpler terms,
NLP allows people to manipulate as well as have texts analyzed
in a
number like manner. The capabilities of numbers include the
fact they are known for being great, this is because it is
considered to
be easy to add, average, compare in addition to learning all
manner of things such as revenue comparisons or consumer
trends on
their spending within a given period. NLP also has its own
limitations which include variety as well as ambiguity in text,

data
availability nowadays most of NLP tends to be generated
through the use of models which are considered to be machine-
learned
(Lee, et.al, 2020). Exercise: There are several packages which
are mainly implemented in the process of text mining as well as
data
mining which include; Civis- this package is mainly considered
to be an end to end, easy to use as well as an extendable
platform of data science which is within the cloud, created by
scientists of data, for any team which desires to make great
decisions
which are driven by data to make it possible for their
organizations be driven in the forward direction. Another
package which
is used in the process is considered to be the CMSR Data Miner
which is basically created for the enterprise data which is
known to
have database focus, which is also known for incorporating the
rule engine, decision tree, neural clustering, neural network,
hotspot
drill down, cross sell analysis, cross table deviation analysis,
charts and visualization in addition to many more. An additional
package which is also used in data mining as well as text
mining includes the Coheris SPAD, this package is basically
known for
providing exploratory analyses which are known to be powerful
as well as gadgets for data mining which include clustering,
PCA,
decision trees that are interactive, analyses that are
discriminant, networks that are neural, text mining in addition
to many more
others, all through GUI which is user friendly.

1
2
3
4
2
5
6
5
There is also the package of AdvancedMiner which is from
Algolytics, it mainly offers tools of a wider range which are
used in
transformations of data, models of mining data, analysis of data
as well as reporting of data (Silge and Robinson, 2017).
References
Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E.
D., Gutierrez, J. B., &Kochut, K. (2017). A brief survey of text
mining:
Classification, clustering and extraction techniques. arXiv
preprint arXiv:1707.02919. Retrieved from
https://arxiv.org/abs/1707.02919
Kong, X., & Gerstein, M. B. (2018). Text mining systems

biology: Turning the microscope back on the observer. Current
Opinion in Systems Biology, 11, 117-122. Retrieved from
5
7
8 9
10 10
11
Source Matches (20)
Student paper 86%
Student paper 65%
Student paper 100%
Student paper 89%
Student paper 67%
kdnuggets 69%
kdnuggets 76%
https://www.sciencedirect.com/science/article/pii/S2452310018
300787
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., &

Kang, J. (2020).BioBERT: a pre-trained biomedical language
representation model for biomedical text mining.
Bioinformatics, 36(4), 1234-1240. Retrieved from
https://academic.oup.com/bioinformatics/article/36/4/1234/5566
506
Sharda, R., Delen, D., Turban, E., Aronson, J., & Liang, T.
(2014). Business intelligence and analytics. System for
Decesion
Support. Silge, J., & Robinson, D. (2017). Text mining with R:
A tidy approach. " O'Reilly Media, Inc.". Retrieved from
https://books.google.co.ke/books?
hl=en&lr=&id=qNcnDwAAQBAJ&oi=fnd&pg=PP1&dq=text+m
ining&ots=Q0DPdoJVxY&sig=RgpTzQUatkh-
2e0nqQ6TW6ENTw4&redir_esc=y#v=onepage&q=text%20mini
ng&f=false
8 8
12
3 1
13
1
Student paper
ASSIGNMENT 4 1
Original source

WEEK 4 ASSIGNMENT 1
2
Student paper
ASSIGNMENT 4 2
Original source
Week 4 Assignment
3
Student paper
Original source
4
Student paper
Business Intelligence ITS 531 – 06
Summer 2020 First Bi-Term
Original source
Business Intelligence ITS 531 – 06
Summer 2020 First Bi-Term

2
Student paper
Text mining is identified as a set of
procedure needed to convert text
documents that are unstructured or
resources to structured information
which is valuable.
Original source
Text mining encompasses a set of
processes employed in turning
unstructured text resources or
documents into valuable, structured
information
5
Student paper
Civis- this package is mainly
considered to be an end to end,
easy to use as well as an extendable
platform of data science which is
within the cloud, created by
scientists of data, for any team
which desires to make great
decisions which are driven by data
to make it possible for their
organizations be driven in the
forward direction.
Original source

Civis, an easy-to-use, end-to-end,
extendable, data science platform in
the cloud, built by data scientists, for
teams who want to make great data-
driven decisions to drive their
organizations forward
6
Student paper
Another package which is used in
the process is considered to be the
CMSR Data Miner which is basically
created for the enterprise data
which is known to have database
focus, which is also known for
incorporating the rule engine,
decision tree, neural clustering,
neural network, hotspot drill down,
cross sell analysis, cross table
deviation analysis, charts and
visualization in addition to many
more.
Original source
CMSR Data Miner, built for business
data with database focus,
incorporating rule-engine, neural
network, neural clustering (SOM),
decision tree, hotspot drill-down,
cross table deviation analysis, cross-
sell analysis, visualization/charts,
and more

kdnuggets 64%
kupdf 73%
Student paper 73%
Student paper 86%
papers 86%
papers 100%
Student paper 88%
Student paper 100%
Student paper 100%
Student paper 66%
Student paper 75%
Student paper 82%
Student paper 100%
5
Student paper
An additional package which is also
used in data mining as well as text
mining includes the Coheris SPAD,
this package is basically known for

providing exploratory analyses
which are known to be powerful as
well as gadgets for data mining
which include clustering, PCA,
decision trees that are interactive,
analyses that are discriminant,
networks that are neural, text
mining in addition to many more
others, all through GUI which is user
friendly. There is also the package of
AdvancedMiner which is from
Algolytics, it mainly offers tools of a
wider range which are used in
transformations of data, models of
mining data, analysis of data as well
as reporting of data (Silge and
Robinson, 2017).
Original source
Coheris SPAD, provides powerful
exploratory analyses and data
mining tools, including PCA,
clustering, interactive decision trees,
discriminant analyses, neural
networks, text mining and more, all
via user-friendly GUI AdvancedMiner
from Algolytics, provides a wide
range of tools for data
transformations, Data Mining
models, data analysis and reporting
7
Student paper

A brief survey of text mining:
Original source
A Survey of Text Mining Techniques
and
8
Student paper
Classification, clustering and
extraction techniques.
Original source
Feature extraction, classification,
and clustering A
9
Student paper
Retrieved from
Original source
Retrieved from
10
Student paper
Kong, X., & Gerstein, M.

Original source
X Kong, M Gerstein (2018)
10
Student paper
Text mining systems biology:
Turning the microscope back on the
observer. Current Opinion in
Systems Biology, 11, 117-122.
Original source
Text mining systems biology Turning
the microscope back on the
observer Current Opinion in
Systems Biology 11:117-122
11
Student paper
Retrieved from
https://www.sciencedirect.com/scien
ce/article/pii/S2452310018300787
Original source
Retrieved from
https://www.sciencedirect.com/scien
ce/article/pii/S0167739X16306963
8

Student paper
Lee, J., Yoon, W., Kim, S., Kim, D.,
Kim, S., So, C. H., & Kang, J.
Original source
Lee, J., Yoon, W., Kim, S., Kim, D.,
Kim, S., So, C H., & Kang, J
8
Student paper
a pre-trained biomedical language
representation model for
biomedical text mining.
Bioinformatics, 36(4), 1234-1240.
Original source
a pre-trained biomedical language
representation model for
biomedical text mining
Bioinformatics, 36(4), 1234-1240
12
Student paper
Retrieved from
https://academic.oup.com/bioinfor
matics/article/36/4/1234/5566506
Original source

Retrieved from
https://academic.oup.com/bioinfor
matics/article/33/21/3364/3885699
3
Student paper
Sharda, R., Delen, D., Turban, E.,
Aronson, J., & Liang, T.
Original source
Sharda, R., Delen, D., Turban, E
1
Student paper
Business intelligence and analytics.
Original source
(2012) Business Intelligence and
Analytics
13
Student paper
O'Reilly Media, Inc.".
Original source
O'Reilly Media, Inc."

iii
Preface xxv
About the Authors xxxiv
PART I Introduction to Analytics and AI 1
Chapter 1 Overview of Business Intelligence, Analytics,
Data Science, and Artificial Intelligence: Systems
for Decision Support 2
Chapter 2 Artificial Intelligence: Concepts, Drivers, Major
Technologies, and Business Applications 73
Chapter 3 Nature of Data, Statistical Modeling, and
Visualization 117
PART II Predictive Analytics/Machine Learning 193
Chapter 4 Data Mining Process, Methods, and Algorithms 194
Chapter 5 Machine-Learning Techniques for Predictive
Analytics 251
Chapter 6 Deep Learning and Cognitive Computing 315
Chapter 7 Text Mining, Sentiment Analysis, and Social
Analytics 388
PART III Prescriptive Analytics and Big Data 459
Chapter 8 Prescriptive Analytics: Optimization and

Simulation 460
Chapter 9 Big Data, Cloud Computing, and Location Analytics:
Concepts and Tools 509
PART IV Robotics, Social Networks, AI and IoT 579
Chapter 10 Robotics: Industrial and Consumer Applications 580
Chapter 11 Group Decision Making, Collaborative Systems,
and
AI Support 610
Chapter 12 Knowledge Systems: Expert Systems,
Recommenders,
Chatbots, Virtual Personal Assistants, and Robo
Advisors 648
Chapter 13 The Internet of Things as a Platform for Intelligent
Applications 687
PART V Caveats of Analytics and AI 725
Chapter 14 Implementation Issues: From Ethics and Privacy to
Organizational and Societal Impacts 726
Glossary 770
Index 785
BRIEF CONTENTS
A01_SHAR2016_11_SE_FM.indd 3 21/12/18 1:43 PM
iv

CONTENTS
Preface xxv
About the Authors xxxiv
PART I Introduction to Analytics and AI 1
Chapter 1 Overview of Business Intelligence, Analytics, Data
Science, and Artificial Intelligence: Systems for Decision
Support 2
1.1 Opening Vignette: How Intelligent Systems Work for
KONE Elevators and Escalators Company 3
1.2 Changing Business Environments and Evolving Needs for
Decision Support and Analytics 5
Decision-Making Process 6
The Influence of the External and Internal Environments on the
Process 6
Data and Its Analysis in Decision Making 7
Technologies for Data Analysis and Decision Support 7
1.3 Decision-Making Processes and Computerized Decision
Support Framework 9
Simon’s Process: Intelligence, Design, and Choice 9
The Intelligence Phase: Problem (or Opportunity) Identification
10
0 APPLICATION CASE 1.1 Making Elevators Go Faster! 11

The Design Phase 12
The Choice Phase 13
The Implementation Phase 13
The Classical Decision Support System Framework 14
A DSS Application 16
Components of a Decision Support System 18
The Data Management Subsystem 18
The Model Management Subsystem 19
0 APPLICATION CASE 1.2 SNAP DSS Helps OneNet Make
Telecommunications Rate Decisions 20
The User Interface Subsystem 20
The Knowledge-Based Management Subsystem 21
1.4 Evolution of Computerized Decision Support to Business
Intelligence/Analytics/Data Science 22
A Framework for Business Intelligence 25
The Architecture of BI 25
The Origins and Drivers of BI 26
Data Warehouse as a Foundation for Business Intelligence 27
Transaction Processing versus Analytic Processing 27

A Multimedia Exercise in Business Intelligence 28
Contents v
1.5 Analytics Overview 30
Descriptive Analytics 32
0 APPLICATION CASE 1.3 Silvaris Increases Business with
Visual
Analysis and Real-Time Reporting Capabilities 32
0 APPLICATION CASE 1.4 Siemens Reduces Cost with the
Use of Data
Visualization 33
Predictive Analytics 33
0 APPLICATION CASE 1.5 Analyzing Athletic Injuries 34
Prescriptive Analytics 34
0 APPLICATION CASE 1.6 A Specialty Steel Bar Company
Uses Analytics
to Determine Available-to-Promise Dates 35
1.6 Analytics Examples in Selected Domains 38
Sports Analytics—An Exciting Frontier for Learning and
Understanding
Applications of Analytics 38

Analytics Applications in Healthcare—Humana Examples 43
0 APPLICATION CASE 1.7 Image Analysis Helps Estimate
Plant Cover 50
1.7 Artificial Intelligence Overview 52
What Is Artificial Intelligence? 52
The Major Benefits of AI 52
The Landscape of AI 52
0 APPLICATION CASE 1.8 AI Increases Passengers’ Comfort
and
Security in Airports and Borders 54
The Three Flavors of AI Decisions 55
Autonomous AI 55
Societal Impacts 56
0 APPLICATION CASE 1.9 Robots Took the Job of Camel-
Racing Jockeys
for Societal Benefits 58
1.8 Convergence of Analytics and AI 59
Major Differences between Analytics and AI 59
Why Combine Intelligent Systems? 60
How Convergence Can Help? 60
Big Data Is Empowering AI Technologies 60

The Convergence of AI and the IoT 61
The Convergence with Blockchain and Other Technologies 62
0 APPLICATION CASE 1.10 Amazon Go Is Open for Business
62
IBM and Microsoft Support for Intelligent Systems
Convergence 63
1.9 Overview of the Analytics Ecosystem 63
1.10 Plan of the Book 65
1.11 Resources, Links, and the Teradata University Network
Connection 66
Resources and Links 66
Vendors, Products, and Demos 66
Periodicals 67
The Teradata University Network Connection 67
vi Contents
The Book’s Web Site 67
Chapter Highlights 67 • Key Terms 68
Questions for Discussion 68 • Exercises 69
References 70

Chapter 2 Artificial Intelligence: Concepts, Drivers, Major
Technologies, and Business Applications 73
2.1 Opening Vignette: INRIX Solves Transportation
Problems 74
2.2 Introduction to Artificial Intelligence 76
Definitions 76
Major Characteristics of AI Machines 77
Major Elements of AI 77
AI Applications 78
Major Goals of AI 78
Drivers of AI 79
Benefits of AI 79
Some Limitations of AI Machines 81
Three Flavors of AI Decisions 81
Artificial Brain 82
2.3 Human and Computer Intelligence 83
What Is Intelligence? 83
How Intelligent Is AI? 84
Measuring AI 85

0 APPLICATION CASE 2.1 How Smart Can a Vacuum Cleaner
Be? 86
2.4 Major AI Technologies and Some Derivatives 87
Intelligent Agents 87
Machine Learning 88
0 APPLICATION CASE 2.2 How Machine Learning Is
Improving Work
in Business 89
Machine and Computer Vision 90
Robotic Systems 91
Natural Language Processing 92
Knowledge and Expert Systems and Recommenders 93
Chatbots 94
Emerging AI Technologies 94
2.5 AI Support for Decision Making 95
Some Issues and Factors in Using AI in Decision Making 96
AI Support of the Decision-Making Process 96
Automated Decision Making 97
0 APPLICATION CASE 2.3 How Companies Solve Real-
World Problems
Using Google’s Machine-Learning Tools 97

Conclusion 98
Contents vii
2.6 AI Applications in Accounting 99
AI in Accounting: An Overview 99
AI in Big Accounting Companies 100
Accounting Applications in Small Firms 100
0 APPLICATION CASE 2.4 How EY, Deloitte, and PwC Are
Using AI 100
Job of Accountants 101
2.7 AI Applications in Financial Services 101
AI Activities in Financial Services 101
AI in Banking: An Overview 101
Illustrative AI Applications in Banking 102
Insurance Services 103
0 APPLICATION CASE 2.5 US Bank Customer Recognition
and
Services 104
2.8 AI in Human Resource Management (HRM) 105

AI in HRM: An Overview 105
AI in Onboarding 105
0 APPLICATION CASE 2.6 How Alexander Mann
Solution
s (AMS) Is
Using AI to Support the Recruiting Process 106
Introducing AI to HRM Operations 106
2.9 AI in Marketing, Advertising, and CRM 107
Overview of Major Applications 107
AI Marketing Assistants in Action 108
Customer Experiences and CRM 108
0 APPLICATION CASE 2.7 Kraft Foods Uses AI for
Marketing
and CRM 109

Other Uses of AI in Marketing 110
2.10 AI Applications in Production-Operation
Management (POM) 110
AI in Manufacturing 110
Implementation Model 111
Intelligent Factories 111
Logistics and Transportation 112
References 114
Chapter 3 Nature of Data, Statistical Modeling, and
Visualization 117
3.1 Opening Vignette: SiriusXM Attracts and Engages a
New Generation of Radio Consumers with Data-Driven
Marketing 118

3.2 Nature of Data 121
3.3 Simple Taxonomy of Data 125
0 APPLICATION CASE 3.1 Verizon Answers the Call for
Innovation: The
Nation’s Largest Network Provider uses Advanced Analytics to
Bring
the Future to its Customers 127
viii Contents
3.4 Art and Science of Data Preprocessing 129
0 APPLICATION CASE 3.2 Improving Student Retention with
Data-Driven Analytics 133
3.5 Statistical Modeling for Business Analytics 139
Descriptive Statistics for Descriptive Analytics 140

Measures of Centrality Tendency (Also Called Measures of
Location or
Centrality) 140
Arithmetic Mean 140
Median 141
Mode 141
Measures of Dispersion (Also Called Measures of Spread or
Decentrality) 142
Range 142
Variance 142
Standard Deviation 143
Mean Absolute Deviation 143
Quartiles and Interquartile Range 143
Box-and-Whiskers Plot 143

Shape of a Distribution 145
0 APPLICATION CASE 3.3 Town of Cary Uses Analytics to
Analyze Data
from Sensors, Assess Demand, and Detect Problems 150
3.6 Regression Modeling for Inferential Statistics 151
How Do We Develop the Linear Regression Model? 152
How Do We Know If the Model Is Good Enough? 153
What Are the Most Important Assumptions in Linear
Regression? 154
Logistic Regression 155
Time-Series Forecasting 156
0 APPLICATION CASE 3.4 Predicting NCAA Bowl Game
Outcomes 157
3.7 Business Reporting 163
0 APPLICATION CASE 3.5 Flood of Paper Ends at FEMA 165
3.8 Data Visualization 166

Brief History of Data Visualization 167
0 APPLICATION CASE 3.6 Macfarlan Smith Improves
Operational
Performance Insight with Tableau Online 169
3.9 Different Types of Charts and Graphs 171
Basic Charts and Graphs 171
Specialized Charts and Graphs 172
Which Chart or Graph Should You Use? 174
3.10 Emergence of Visual Analytics 176
Visual Analytics 178
High-Powered Visual Analytics Environments 180
3.11 Information Dashboards 182

Contents ix
0 APPLICATION CASE 3.7 Dallas Cowboys Score Big with
Tableau
and Teknion 184
Dashboard Design 184
0 APPLICATION CASE 3.8 Visual Analytics Helps Energy
Supplier Make
Better Connections 185
What to Look for in a Dashboard 186
Best Practices in Dashboard Design 187
Benchmark Key Performance Indicators with Industry Standards
187
Wrap the Dashboard Metrics with Contextual Metadata 187
Validate the Dashboard Design by a Usability Specialist 187

Prioritize and Rank Alerts/Exceptions Streamed to the
Dashboard 188
Enrich the Dashboard with Business-User Comments 188
Present Information in Three Different Levels 188
Pick the Right Visual Construct Using Dashboard Design
Principles 188
Provide for Guided Analytics 188
References 192
PART II Predictive Analytics/Machine Learning 193
Chapter 4 Data Mining Process, Methods, and Algorithms 194
4.1 Opening Vignette: Miami-Dade Police Department Is
Using
Predictive Analytics to Foresee and Fight Crime 195

4.2 Data Mining Concepts 198
0 APPLICATION CASE 4.1 Visa Is Enhancing the Customer
Experience while Reducing Fraud with Predictive Analytics
and Data Mining 199
Definitions, Characteristics, and Benefits 201
How Data Mining Works 202
0 APPLICATION CASE 4.2 American Honda Uses Advanced
Analytics to
Improve Warranty Claims 203
Data Mining Versus Statistics 208
4.3 Data Mining Applications 208
0 APPLICATION CASE 4.3 Predictive Analytic and Data
Mining Help
Stop Terrorist Funding 210
4.4 Data Mining Process 211
Step 1: Business Understanding 212

Step 2: Data Understanding 212
Step 3: Data Preparation 213
Step 4: Model Building 214
0 APPLICATION CASE 4.4 Data Mining Helps in
Cancer Research 214
Step 5: Testing and Evaluation 217
x Contents
Step 6: Deployment 217
Other Data Mining Standardized Processes and Methodologies
217
4.5 Data Mining Methods 220
Classification 220

Estimating the True Accuracy of Classification Models 221
Estimating the Relative Importance of Predictor Variables 224
Cluster Analysis for Data Mining 228
0 APPLICATION CASE 4.5 Influence Health Uses Advanced
Predictive
Analytics to Focus on the Factors That Really Influence
People’s
Healthcare Decisions 229
Association Rule Mining 232
4.6 Data Mining Software Tools 236
0 APPLICATION CASE 4.6 Data Mining goes to Hollywood:
Predicting
Financial Success of Movies 239
4.7 Data Mining Privacy Issues, Myths, and Blunders 242
0 APPLICATION CASE 4.7 Predicting Customer Buying
Patterns—The

Target Story 243
Data Mining Myths and Blunders 244
References 250
Chapter 5 Machine-Learning Techniques for Predictive
Analytics 251
5.1 Opening Vignette: Predictive Modeling Helps
Better Understand and Manage Complex Medical
Procedures 252
5.2 Basic Concepts of Neural Networks 255
Biological versus Artificial Neural Networks 256
0 APPLICATION CASE 5.1 Neural Networks are Helping to
Save
Lives in the Mining Industry 258
5.3 Neural Network Architectures 259

Kohonen’s Self-Organizing Feature Maps 259
Hopfield Networks 260
0 APPLICATION CASE 5.2 Predictive Modeling Is Powering
the Power
Generators 261
5.4 Support Vector Machines 263
0 APPLICATION CASE 5.3 Identifying Injury Severity Risk
Factors in
Vehicle Crashes with Predictive Analytics 264
Mathematical Formulation of SVM 269
Primal Form 269
Dual Form 269
Soft Margin 270
Nonlinear Classification 270

Kernel Trick 271
Contents xi
5.5 Process-Based Approach to the Use of SVM 271
Support Vector Machines versus Artificial Neural Networks 273
5.6 Nearest Neighbor Method for Prediction 274
Similarity Measure: The Distance Metric 275
Parameter Selection 275
0 APPLICATION CASE 5.4 Efficient Image Recognition and
Categorization with knn 277
5.7 Naïve Bayes Method for Classification 278
Bayes Theorem 279

Naïve Bayes Classifier 279
Process of Developing a Naïve Bayes Classifier 280
Testing Phase 281
0 APPLICATION CASE 5.5 Predicting Disease Progress in
Crohn’s
Disease Patients: A Comparison of Analytics Methods 282
5.8 Bayesian Networks 287
How Does BN Work? 287
How Can BN Be Constructed? 288
5.9 Ensemble Modeling 293
Motivation—Why Do We Need to Use Ensembles? 293
Different Types of Ensembles 295
Bagging 296
Boosting 298

Variants of Bagging and Boosting 299
Stacking 300
Information Fusion 300
Summary—Ensembles are not Perfect! 301
0 APPLICATION CASE 5.6 To Imprison or Not to Imprison:
A Predictive Analytics-Based Decision Support System for
Drug Courts 304
Internet Exercises 312 • References 313
Chapter 6 Deep Learning and Cognitive Computing 315
6.1 Opening Vignette: Fighting Fraud with Deep Learning
and Artificial Intelligence 316
6.2 Introduction to Deep Learning 320

0 APPLICATION CASE 6.1 Finding the Next Football Star
with
Artificial Intelligence 323
6.3 Basics of “Shallow” Neural Networks 325
0 APPLICATION CASE 6.2 Gaming Companies Use Data
Analytics to
Score Points with Players 328
0 APPLICATION CASE 6.3 Artificial Intelligence Helps
Protect Animals
from Extinction 333
xii Contents
6.4 Process of Developing Neural Network–Based
Systems 334
Learning Process in ANN 335

Backpropagation for ANN Training 336
6.5 Illuminating the Black Box of ANN 340
0 APPLICATION CASE 6.4 Sensitivity Analysis Reveals
Injury Severity
Factors in Traffic Accidents 341
6.6 Deep Neural Networks 343
Feedforward Multilayer Perceptron (MLP)-Type Deep Networks
343
Impact of Random Weights in Deep MLP 344
More Hidden Layers versus More Neurons? 345
0 APPLICATION CASE 6.5 Georgia DOT Variable Speed
Limit Analytics
Help Solve Traffic Congestions 346
6.7 Convolutional Neural Networks 349
Convolution Function 349

Pooling 352
Image Processing Using Convolutional Networks 353
0 APPLICATION CASE 6.6 From Image Recognition to Face
Recognition 356
Text Processing Using Convolutional Networks 357
6.8 Recurrent Networks and Long Short-Term Memory
Networks 360
0 APPLICATION CASE 6.7 Deliver Innovation by
Understanding
Customer Sentiments 363
LSTM Networks Applications 365
6.9 Computer Frameworks for Implementation of Deep
Learning 368
Torch 368
Caffe 368

TensorFlow 369
Theano 369
Keras: An Application Programming Interface 370
6.10 Cognitive Computing 370
How Does Cognitive Computing Work? 371
How Does Cognitive Computing Differ from AI? 372
Cognitive Search 374
IBM Watson: Analytics at Its Best 375
0 APPLICATION CASE 6.8 IBM Watson Competes against
the
Best at Jeopardy! 376
How Does Watson Do It? 377
What Is the Future for Watson? 377

References 385
Contents xiii
Chapter 7 Text Mining, Sentiment Analysis, and Social
Analytics 388
7.1 Opening Vignette: Amadori Group Converts Consumer
Sentiments into Near-Real-Time Sales 389
7.2 Text Analytics and Text Mining Overview 392
0 APPLICATION CASE 7.1 Netflix: Using Big Data to Drive
Big
Engagement: Unlocking the Power of Analytics to Drive
Content and Consumer Insight 395
7.3 Natural Language Processing (NLP) 397

0 APPLICATION CASE 7.2 AMC Networks Is Using
Analytics to
Capture New Viewers, Predict Ratings, and Add Value for
Advertisers
in a Multichannel World 399
7.4 Text Mining Applications 402
Marketing Applications 403
Security Applications 403
Biomedical Applications 404
0 APPLICATION CASE 7.3 Mining for Lies 404
Academic Applications 407
0 APPLICATION CASE 7.4 The Magic Behind the Magic:
Instant Access
to Information Helps the Orlando Magic Up their Game and the
Fan’s
Experience 408
7.5 Text Mining Process 410

Task 1: Establish the Corpus 410
Task 2: Create the Term–Document Matrix 411
Task 3: Extract the Knowledge 413
0 APPLICATION CASE 7.5 Research Literature Survey with
Text
Mining 415
7.6 Sentiment Analysis 418
0 APPLICATION CASE 7.6 Creating a Unique Digital
Experience to
Capture Moments That Matter at Wimbledon 419
Sentiment Analysis Applications 422
Sentiment Analysis Process 424
Methods for Polarity Identification 426
Using a Lexicon 426

Using a Collection of Training Documents 427
Identifying Semantic Orientation of Sentences and Phrases 428
Identifying Semantic Orientation of Documents 428
7.7 Web Mining Overview 429
Web Content and Web Structure Mining 431
7.8 Search Engines 433
Anatomy of a Search Engine 434
1. Development Cycle 434
2. Response Cycle 435
Search Engine Optimization 436
Methods for Search Engine Optimization 437

xiv Contents
0 APPLICATION CASE 7.7 Delivering Individualized Content
and
Driving Digital Engagement: How Barbour Collected More
Than 49,000
New Leads in One Month with Teradata Interactive 439
7.9 Web Usage Mining (Web Analytics) 441
Web Analytics Technologies 441
Web Analytics Metrics 442
Web Site Usability 442
Traffic Sources 443
Visitor Profiles 444
Conversion Statistics 444
7.10 Social Analytics 446

Social Network Analysis 446
Social Network Analysis Metrics 447
0 APPLICATION CASE 7.8 Tito’s Vodka Establishes Brand
Loyalty with
an Authentic Social Strategy 447
Connections 450
Distributions 450
Segmentation 451
Social Media Analytics 451
How Do People Use Social Media? 452
Measuring the Social Media Impact 453
Best Practices in Social Media Analytics 453

References 457
PART III Prescriptive Analytics and Big Data 459
Chapter 8 Prescriptive Analytics: Optimization and Simulatio n
460
8.1 Opening Vignette: School District of Philadelphia Uses
Prescriptive Analytics to Find Optimal

4CHANGE PROPOSALPRESENTATIONFORFACULTY REVIEWCapston

Recommended

Recommended

More Related Content

Similar to 4CHANGE PROPOSALPRESENTATIONFORFACULTY REVIEWCapston

Similar to 4CHANGE PROPOSALPRESENTATIONFORFACULTY REVIEWCapston (20)

More from drennanmicah

More from drennanmicah (20)

Recently uploaded

Recently uploaded (20)

4CHANGE PROPOSALPRESENTATIONFORFACULTY REVIEWCapston