CIS8008 Business Intelligence Assignment: Data and Privacy Report

This report presents a comprehensive analysis of business intelligence concepts, primarily focusing on two key areas: the My Health Record (MHR) system and loan delinquency prediction. Task 1 critically reviews and discusses the current privacy provisions of the MHR system, drawing on the Australian Digital Health Agency's privacy policy and recent changes to the My Health Record Act. Task 2 involves exploratory data analysis (EDA) of the loan-delinq.csv dataset using RapidMiner, summarizing key findings and their implications. Task 3 utilizes Tableau Desktop to visualize and analyze data related to loan delinquency. The report covers data privacy, data analysis techniques, and the application of business intelligence tools to real-world datasets, aiming to provide insights into data security, and predictive modeling.

Running Head: BUSINESS INTELLIGENCE
Business Intelligence
Name of the Student
Name of the University
Student ID

1BUSINESS INTELLIGENCE
Table of Contents
Task 1...............................................................................................................................................2
Introduction..................................................................................................................................2
Significance of the system of electronic record...........................................................................3
Evolution in Electronically stored health record.........................................................................4
Task 2...............................................................................................................................................8
Task 2.1........................................................................................................................................8
Task 2.2......................................................................................................................................17
Task 2.3......................................................................................................................................19
Task 2.4......................................................................................................................................21
Task 3.............................................................................................................................................23
Task 3.1......................................................................................................................................23
Task 3.2......................................................................................................................................24
Task 3.3......................................................................................................................................25
Task 3.4......................................................................................................................................26
Task 3.5......................................................................................................................................27
List of References..........................................................................................................................29

2BUSINESS INTELLIGENCE
Task 1
Introduction
Research in health and associated policy of privacy s of great importance for the entire
society. Research in health plays an important role in improving health care service. In any
organization an important asset is the information belong to the various information. Some of
this information is extremely confidential and therefore, therefore confidentiality of the
information should be protected. Security to information refers to protection of important
information and the associated hardware used to protect the information (Gowtham et al. 2017).
The term security refers to a composite system including both internal and external operation
such that the collected data and information remain protected and confidential. Information
security has several functions to play. These include protection of data collected by the
organization, protection of organization’s capacity in carrying out assigned work and security to
technology assets used by the organization. The security to information is important in the sense
that misuse to information resulted from weak protection of information has the potential
distortionary effect on lives of many people associated with the organization.
Australia Digital Health Agency is responsible for handling all health related information
of Australians. In the past few decades, there is an increasing tendency to gather various types of
information related to health care (Digitalhealth.gov.au. 2018). Increasing involvement of
various people to receive health care service and presence of few group of service providers
make is extremely important to document detail information regarding health condition.
Technological innovation in machinery and equipment used for diagnosis and different therapies
leads to an increase in availability of information related to individual (Zhang et al. 2017).
Among various types of available data, the one that is most easily available the data of prenatal

3BUSINESS INTELLIGENCE
testing. The continuity in health care service is also subject to proper documentation of
associated risk factors. This can also be considered as a method for protecting against any type of
allegation of malpractice. Primary health care offers various services in addition to direct health
care. The health care service providers record their observation, impression and instructions. In
the system, often third party intervention is observed where they use the information to pay for
different health care services.
Significance of the system of electronic record
Today, health care sectors place great importance to protection of privacy of the collected
information. The electronically saved health record should be kept confidentially. This is due the
fact accessing large volume of health care information today has become very become. It is
therefore very easy to misuse the confidential information. The electronic media is used to store
health care data, as it is not possible to keep photocopy of each of the document containing
medical report. The process of photocopying is no convenient as it is both laborious and time
consuming. The second aspect related to health care data is that electronic media based data has
now considered as a valuable asset (Zhang et al. 2015). It is observed that, various competing
companies collect information from the Physicians and different pharmacies regarding other
companies’ sale to increase their competitiveness and earn a higher incentive.
Data gathered from various sources are first combined and then are connected to others’
profile. It becomes easier to extract data from remote location and explore the database within
the build network when data are saved electronically. This however possess a high risk of third
party access to the information. In the absence of proper security system to protect the
organization database, it is easy for anyone to access the data without leaving any trace of such
mishap (Legislation.gov.au 2018). The service providers can easily understand trend of the data

4BUSINESS INTELLIGENCE
series containing information regarding health condition of the whole population. The electronic
record system provides information about the kind of medical treatment used by most of the
people. The providers then can use the information in designing health care service in favor of
most frequently used medical care service (Legislation.gov.au. 2018). This information is useful
in undertaking preventive measures. The most recent technological advancement in the medical
care industry is impairment of electronic health care record with mobile technology (Hasanain,
Vallmuur and Clark 2015). The HER is also playing an important role in the industry.
Continuous evolution of the system along with improvement in the overall quality of health care
service is an important contribution of the system. The electronic based system has an advantage
over the paper based terms in terms of saving time and efforts of the service providers. This in
turn contributes to an increasing flow of service providers in recent years.
As the information related to status of health and financial management related to
individual patients are stored electronically then errors in processing the information is
mitigated. Additionally, this also helps to avoid risk of malpractices in meeting reimbursement
claim. A major drawback of current legal framework for confidentiality is that there is no
variation in obligation related to health care record regarding whether it is stored electronically
or is subject paper based method. The degree of confidentially however vary depending on
information holder and the nature of information kept.
Evolution in Electronically stored health record
With increasing burden of health record, the system of electronically based has
undergone rapid technological changes to offer targeted support to the service providers. Large
variation in a nation creates a room for huge support from utilization of electronic health record.
The market of electronic health record thus undergoes severe changes in recent years depending

5BUSINESS INTELLIGENCE
on the proposition of concerned authorities. In most hospitals, the electronic health record system
plays an important role (Banfield et al., 2017). Therefore, with change in the structure of health
record, there is an associated change in outcome of patients as well. As per the findings of
National Center of Health Statistics, approximately 75 percent service providers are able to
enhance the quality of patient care service by using the electronically stored database. The
function of electronic health record system is not limited to storage of necessary data and
information. It also provides necessary information that can be used for benefits of the patients.
The system contains records regarding when patients take new medication and alerts physicians
about the potential issues. Digital health technology has undergone serious changes in recent
years influencing lives of many people.
The Australian Digital Agency gathers and protects personal information of citizens. The
privacy principles are protected by the organization following the Privacy Act of 1988. The
operators of Health Record System manage the personal information of the organization.
Personal information is considered as an opinion where an individual is identified for
communication and arrangement of business meetings and obligations (Myhealthrecord.gov.au.
2018). The operators maintain ‘My Health Record System’. Information are gathered about
recipients of health care services. Various other records are reported as per operators of
registered repository (Hsiao, Hing and Ashman, 2014).. The legislation of a state or territory
prevents the data from third party sharing. The regulation imposes civil and criminal penalties on
a person subject to accessing, utilizing and information disclosure without valid authorization.
Information in the organization is gathered through the medium of telephone, mail, and
facsimile and from general people and other health care operators. Data are collected on job title,
records of employees, individual image, bank details and work history. The registered

6BUSINESS INTELLIGENCE
information in the healthcare organization helps to identify healthcare service for individual. The
first aid received by an individual is administered in the Agency premises. The agency then
collects the relevant information and discloses the personal information in order to manage
relation with its employees and duty of the organization. There often arise some critical
situations such as conducting deals with the business associates and other contractors,
management of workforce, meeting legislative obligation, delivery of functions, marketing
information associated with goods, services, initiatives or events or offering communication
information. After receiving marketing materials from the organization, the individual might go
for further communication regarding the same. Disclosure of the information to the Human
Service Department provide further support to the health care organization
(Myhealthrecord.gov.au 2018). As the individual appeals to get registered in digital health care
service through the process of Document Verification Service the agency then in position to
reveal personal information of the applicant. It is not possible to maintain security of the
database gathered through internet. Relevant information are also collected following IP address
of the computer. The cookies and cache files are stored in the agency’s website named
‘www.digitalhealth.gov.au.’ The geo-location corresponding to the IP address is used by the
agency to determine particular location. Information can also be gathered from download or sign
up drop box option.
Common people possesses the right to request an access or correction of current
information reported in the Agency. Before providing information access to the individual, the
agency confirms identity of the individual. The agency always attempts to make a quick response
to any complaints or enquiries of individual participant (Pearce and Bainbridge 2014). The
parental responsibility related to healthcare of a recipient be act as an authorized representative is

7BUSINESS INTELLIGENCE
strictly restricted under the age of 18. The action of healthcare recipient depends on the purpose
of the act. Such healthcare act influences the service recipient depending on modification of the
prescribed regulation.

8BUSINESS INTELLIGENCE
Task 2
Task 2.1
Table 2.1 shows the results of the exploratory data analysis on the variables involved in
the dataset “loan.delinq.csv”. This research is mainly based on prediction of the fact whether a
person is delinquent to loan or not. In order to evaluate that, several information on the status of
the loan taken by the people are recorded. All the information is not necessary to be considered
in the prediction model. Some must have significant impact on the evaluation of delinquency and
some other variables might not affect the fact. In order to identify the variables that are most
closely related to the predictor, the exploratory data analysis has been conducted. All the analysis
in this section has been conducted in the software RapidMiner.
In the dataset. The variable “SeriousDlqn2yrs” is the predictor variable. From the
analysis, it has been observed that the number of persons that are loan delinquent are 139974.
This is denoted by the value “0” and the number of persons that are not delinquent to loans are
10026 and this is denoted by the value “1”. Thus, this variable is a dichotomous variables
involving only two values “0” and “1”. This is the predictor variable, that is, the variable that
will be predicted using statistical models. The second variable is the
“RevolvingUtilizationOfUnsecuredLines”, which is a continuous variable. The variable indicates
the total balance on the credit cards and on the personal lines of credit. These values do not
include the real estate or any kinds on debts that are to be paid in installments such as car loans.
Thus, the average balance on the credit cards of the people have been obtained as $5.75 with the
balance ranging between $0 to $50,708. This indicates that most people do not have much credit
card balance but some people have extremely high credit card balances due. The next considered
variable is the age of the people who have borrowed money. Age of the people is also a

9BUSINESS INTELLIGENCE
continuous variable and the average age of the people borrowing money has been obtained as
52.29 years when the range of the age of the borrowers have been found to be between 0 years
and 109 years. The variable that has been considered next is “NumberOfTime30 –
59DayaPastDueNotWorse”. This variable indicates the number of times a borrower has passed
the due date by 30 – 59 days but not more than that in the last 2 years. The range of values for
this variable has been found to be 0 – 98 times. The average number of times a person misses
this due date has been obtained to be 0.421. “DebtRatio” is the next variable that has been
considered here. This variable indicates the payment of the debts monthly along with the
alimony and the living costs divided by the gross monthly income of the borrower. The debt ratio
ranges between 0 to 329664 and with an average ratio of 353.005. Most of the borrowers have
been observed to have a monthly income of around $5,000. The variable
“AverageNumberOfOpenCreditLinesAndLoans” indicate the number of open loans such as the
EMI’s of car loan, real estate loan or even the credit card loans. The average of the number of
open loans has been found to be 8.45 with a range between 0 and 58. The variable
“NumberOfTimes90DaysLate” indicates the number of times a borrower is past the due date.
The number of times vary between 0 and 98 times. The average number of times being 90 days
late has been observed to be 0.27. Number of mortgage and real estate loans including home
equity lines of credit denoted by the variable “NumberRealEstateLoansOrLines” have been
found to vary between 0 and 54 tomes with an average of 0.11 times. The variable that has been
considered next is “NumberOfTime60 – 89DayaPastDueNotWorse”. This variable indicates the
number of times a borrower has passed the due date by 60 – 89 days but not more than that in the
last 2 years. The range of values for this variable has been found to be 0 – 98 times. The average
number of times a person misses this due date has been obtained to be 0.24. From the analysis, it

10BUSINESS INTELLIGENCE
has also been observed that most of the borrowers stay alone and there are no dependents in their
families.
The graphs showing the nature of the variables along with the exploratory data analysis
results are given in the following figures and tables.
Table 2.1: Results of Exploratory Data Analysis for loan.delinq.csv

11BUSINESS INTELLIGENCE
Figure 1
Figure 2