DATA MINING 1

Data mining

1 Determine the benefits of data mining to the businesses when employing:

a) Predictive analytics to understand the behavior of customers

Predictive analysis provides numerous benefits in businesses. It allows the business

personnel to rank customers in the market share (Fuzion Analytics, 2012). It is a single value

measured for each customer. In addition, it is a reliable campaign to response predictor when

handling customers ranked highly by the business personnel. This constitutes key form of

business intelligence. Through this model, the businessman extracts financial information of the

customer such as credit transactions to enable him determine if the customer is liable for future

business transaction (Fuzion Analytics, 2012). The predictive analysis will outlay prospects of

retaining customers with similar transaction behavior. For instance a customer who spends less

in online business may be less likely to renew annual subscription to the same online business

service. Predictive analysis will also help the business person to conduct smarter rankings

through combined prediction. The right combination allows the business to perform better since

the business personnel consider multiple aspects of the customer and their behaviors. Combined

prediction must be richer and more complex by combining dozen of predictors.

This model allows business institutions to exploit patterns in transactional data to identify risks

and opportunity (Fuzion Analytics, 2012). It captures factors that that facilitate assessment of

risk and guides to a set condition of decision making. The effectiveness of predictive analysis in

data mining allows the businessman to predict loss and profit. The information gathered from
DATA MINING 2

predictive analysis is suitable for long term care of the business in claim management, pricing

and reserving customer service.

b) Associations discovery in products sold to customers

Association discovery model discovers interesting relation between products in large

scale transaction data records. It aids the business person to research and identify the relationship

between seemingly unrelated data. For instance if a person buys egg he or she is more likely

going to buy milk as well. The main rule behind this aspect is the paradox relationship between

products and the consumer determines his decision with an antecedent ‘if’ and the consequence

‘then’. Such decision can be used in promotional pricing or product placement. This aspect of

data mining is most applicable in predicting trends in customer behavior.

c) Web mining to discover business intelligence from Web customers

Web mining is a technique used by business persons to peruse through various web

resources to gather useful information and pattern used in understanding market dynamics (Web

Data Mining, n.d.). The collected information instills more knowledge to the businessman hence

they are able to carry out prediction of customer preference. This aspect not only serves the

interests of consumers but also predicting the right organizational department’s decisions. The

information collected helps to develop more advanced protective measures to be undertaken to

prevent fraudulent business transactions (Web Data Mining, n.d.).

D) Clustering to find related customer information

Clustering in data mining is the task of discovering groups and structures in the data that are

somehow similar. In addition it is applied in segmenting customer and market share as well as

the pattern and categorizing hierarchical density based business models. After understanding the
DATA MINING 3

business categories the businessman is able to summarize and make positive assumption of the

market segment. Another benefit is that one is able to eliminate outliers in the collected data.

2. Assess the reliability of the data mining algorithms. Decide if they can be trusted and

predict the errors they are likely to produce.

The reliability of data mining is an important requirement in deriving and extracting

meaningful information (Rocco, 2011). The success of data mining depends on skill and

knowledge and ingenuity of the business researcher. The data collected by business entity

enhances services rendered as well as product life cycle. Improving the products lifecycle the

businesses is confident for high reliability. There are five major elements for a reliable data

mining process. These elements include;

Extracting, transforming and loading transaction data onto a data warehouse system.

Storing and managing the data in the database system.

Provide the data access to business analysts and IT professionals

Analyze the data with the appropriate application software

Present the data in a useful format

In addition to the elements, there are basic modeling principles that control how business

researchers in data mining (Rocco, 2011). These models provide purpose and predicting

consumer behavior. However, there are problems associated with data mining. Data mining can

be trusted since it has been used with an intention to uncover hidden patterns (Golriz, Behrouz,

& Malihe, 2011). For many years business, scientist engineers and government use data mining

to sift through large volume of data in order to predict upcoming trends. The data mining

algorithm allows the researcher to make comparison between variables in a phenomenon (Rocco,
DATA MINING 4

2011). The main problem is determining a mathematical model for an unknown input or output

data. Typically the algorithms are aimed to reduce failures and minimize consequences

associated with such. The failures are noted when there is an interruption otr the system stops

functioning. Fault detection is determined through two approaches; the model based approach

and data based approach. These techniques are popular in solving such faults and failures within

the system (Golriz, Behrouz & Malihe, 2011).

3 Analyze privacy concerns raised by the collection of personal data for mining purposes.

a. Choose and describe three (3) concerns raised by consumers.

Data mining process raises concerns among consumer privacy. The privacy infringement is

associated with liberty, autonomy solitude and secrecy (Tavani, 1999). The main concern raised

by most consumers is information privacy. This concern intrudes and interferes with personal

information that is regarded as confidential. This results to breach of psychological privacy or

associative privacy. This violation is contributed by;

i) The technology collecting information about consumers without their knowledge

(Tavani, 1999).

ii) Consumers have the knowledge that their private information is being used by

business researchers but they have no say on how the information is being disclosed.

iii) There are no laws protecting consumers from the breach of confidential data

especially in the World Wide Web (Tavani, 1999).

b) Decide if each of these concerns is valid and explain your decision for each.

All the concerns raised are valid.

i) Data mining programs and technology are designed to reveal information that is extremely

difficult for data users to obtain without personal consent (Tavani, 1999).
DATA MINING 5

ii) The consumers transacting in e-business are required to enter information that they have no

idea how the business person will use them. Crucial information that consumers enter when

logged in to online shops risks the bank accounts.

iii) Most consumers have complained that the privacy act in the international law of trade have

not covered privacy information for consumers. For instance US privacy Act of 1974 and data

protection guidelines have not covered privacy information collected from consumers.

c) Describe how each concern is being allayed.

i) The privacy and security of user information is a delicate issue and business persons are taking

into consideration the sensitivity of the matter (Dileep & Swaroop, 2013). Business persons have

vowed to keep the confidential information a secret in order to win the confidence of the

consumers.

ii) Public policies are being formulated with the interest of safeguarding consumers from

criminal activities and fraudulent transactions. Governments, public lawmakers, media,

controller and privacy advocates have focused on key online privacy security issues and

concerns raised by consumers. They enlighten the public on self-regulation and user privacy

measures (Dileep & Swaroop, 2013).

iii) Laws and regulatory trends are taking a new outlook in detecting invasion of new security

issues. The laws seek to expose criminal records, bad online shopping habits, illegal online

banking and fraudulent creditors (Dileep & Swaroop, 2013).

4) Provide at least three (3) examples where businesses have used predictive analysis to

gain a competitive advantage and evaluate the effectiveness of each business’s strategy.

There are several companies that use predictive analysis to enhance their competitive

advantages. For instance chase bank uses predictive analysis to improve customer service. The
DATA MINING 6

bank analyses its data to target customers with interest to them. In addition, it has harnessed the

power of predictive analytics to make decisions. Banks are devising more effective ways to

manage their relationship with consumers. The credit section of the bank has come out strongly

in managing credit lines and collections. The bank boasts of utilizing the power of this aspect to

root out fraud.

Another example is applied by Wal-Mart stores which uses predictive analytic to provide

a tactical insight in enhancing their marketing strategies. This has enabled them to increase

customer retention. On the other hand IBM uses this aspect to predict the confidence of their

consumers and plan their next smart move towards improving customer service. This has enabled

the company to maximize productivity detect and prevent threats. IBM offers easy to use

predictive products and solutions to meet the needs of their consumers.

These institutions have utilized the predictive analytic as a vital decision-making tool with

accuracy and a barrier from an intensely competitive and disruptive economic conditions.
DATA MINING 7

References

Dileep, K. S. & Swaroop, V. (2013). Data Security and Privacy in Data Mining: Research Issues

& Preparation. International Journal of Computer Trends and Technology, 4(2), 2231-

2803.

Fuzion Analytics. (2012). Data Mining and Predictive Analytics in Long-Term Care.

Golriz, A., Behrouz, M., & Malihe B. (2011). A Comparison between Data Mining Prediction

Algorithms for Fault Detection. International Journal of Computer Science Issues, 8,

(6:3), 1694-0814.

Rocco C. M. (2011). Data Mining in Reliability and Risk Assessment. International Journal of

Performability Engineering, 7(1), 3-4.

Tavani, H. T. (1999). Informational privacy, data mining, and the Internet. Ethics and

Information Technology, 1: 137–145.

Web Data Mining. (n.d.) retrieved from http://www.web-datamining.net/