Intelligent Systems for Analytics: Data Mining Techniques Report

This research report delves into the realm of Intelligent Systems for Analytics (ISA), with a specific focus on Data Mining (DM) and its integration with Intelligent Systems (IS). The report defines DM as the process of extracting valuable information from large datasets, highlighting the role of IS in enhancing efficiency and accuracy. It explores various DM techniques and algorithms, including genetic algorithms, artificial neural networks, decision trees, rule induction, and the nearest neighbor method, illustrating their application in knowledge discovery. The report further examines the use of DM in Business Intelligence (BI) and Business Analytics (BA), emphasizing its role in predicting trends and informing proactive decision-making. Real-world applications of DM with IS are presented through case studies, demonstrating its impact across diverse industries. The report concludes by emphasizing the significance of DM in identifying patterns, forecasting future trends, and driving growth across various business domains. References are provided to support the research.

Running Head: IS FOR ANALYTICS
0
Data Mining Techniques with IS
Intelligent Systems for Analytics
(Student Details: )
1/15/2020

IS FOR ANALYTICS
1
Contents
Introduction................................................................................................................................2
Data Mining Techniques with Intelligent Systems....................................................................2
Basic DM Techniques and Algorithms......................................................................................3
Genetic algorithms.................................................................................................................4
Artificial neural networks......................................................................................................4
Decision trees.........................................................................................................................4
Rule induction........................................................................................................................4
Nearest neighbour method.....................................................................................................4
Data visualization...................................................................................................................4
Business Intelligence (BI) using DM techniques...................................................................5
Use of Data Mining in Business Analytics (BA)...................................................................5
Applications of DM with IS...................................................................................................5
Conclusion..................................................................................................................................6
References..................................................................................................................................6

IS FOR ANALYTICS
2
Introduction
This research report is based on research on ‘Intelligent Systems for Analytics’ (ISA) with
some specific area into Intelligent Systems (IS). In general, IS is the system that incorporates
intelligence in useful applications being handled by modern machines. In this context, IS
typically performs optimization as well as search along with extended learning abilities.
Specifically, the report will talk about Data Mining (DM) while exploring different methods
and techniques with the help of IS. Here, DM refers to the practice of evaluating large-level
prevailing databases for further generating completely new information 1. It can be said that
the process of discovering hidden value into the complete data warehouse is known as DM.
In other words, DM is a new technology with high potential for helping modern firms in
order to focus on important facts and information within data warehouses 2. While discussing
IS, the report will narrate how DM tools anticipate upcoming trends as well as behaviours
while enabling businesses to make knowledge-driven and proactive decisions.
Data Mining Techniques with Intelligent Systems
Firstly, the concept of DM needs to be defined as the process of discovering patterns into big
data-sets contains methods at the overlapping of statistics, database systems, and machine
learning 3. Thus, DM can effectively use IS which is an advanced machine learning. IS is
able to learn, perceive and thereby solve critical issues with enhanced accuracy. In addition to
that, there are so many general technologies which are available in the market as well as used
in real-world use like Facebook, Alexa, Siri, self-driving cars and many more 4. In this way,
data mining techniques while using ISs are being discussed and explored here. DM is able to
find useful patterns from a huge amount of data and this process of mining of data becomes
more efficient when IS is integrated into DM techniques. In the process of knowledge
discovery, knowledge mining through data, as well as knowledge extraction, IS plays a vital
role in pattern and data analysis 4.

IS FOR ANALYTICS
3
Source: 5
In this context, DM can be seen as a logical process that is often used to search for big
amounts of data for further finding useful information or data. Here, when ISs are used in
DM techniques, patterns that were previously unknown are identified and studied well. Thus,
after finding patterns, they are used to make important decisions for the effective
development of the businesses 2. The key steps which are involved in DM are as follows:
 Exploration: first of all, data is cleaned as well as transformed in another form during
data exploration. Besides, the determination of key variables as well as the nature of
data is usually done on the basis of relevant problems.
 Pattern identification: post exploring data, this data is defined and refined for some
key variables so that pattern identification can be done. The aim of this step of DM is
to choose and identify the patterns which are capable to make the efficient prediction
about the future.
 Deployment: lastly, these identified patterns of data are deployed for some desired
outcomes 6.
Basic DM Techniques and Algorithms
There are some important types of DM techniques and algorithms include decision trees,
clustering, classification, artificial intelligence, regression, association rules, neural networks,
nearest neighbour method, and genetic algorithms 5. All of the aforementioned methods are

IS FOR ANALYTICS
4
typically used for knowledge discovery through databases. Here, some most commonly used
DM techniques are as follows:
Genetic algorithms
This type of DM technique comes under optimization techniques that often use procedures
like a genetic mutation, genetic combination and natural selection within a design as per the
concepts of evolution 3.
Artificial neural networks
In this context, DM techniques use non-linear predictive models that learn from training as
well as resembling biological neural networks into the proposed structure 7.
Decision trees
Here, DM is done with tree-shaped structures which usually represent decision-sets. It has
been found that such decisions generate specific rules for the dataset classification. In this
context, these specific decision tree methods are CART and CHAID 8.
Rule induction
This DM technique is all about the extraction of the useful if-then rules availed through data
on the basis of statistical significance 2.
Nearest neighbour method
It is worth knowing that the nearest neighbour DM technique is used to classify every record
in a dataset on the basis of the combination of the different classes of k records. This k
records technique is also known as the k-nearest neighbour technique 5.
Data visualization
In this context, the DM uses the visual interpretation of complex relations into multi-
dimensional data for further knowledge extraction and development. In addition to that,
graphics tools are utilized for illustrating data relationships at a large level 4.
All of the above-mentioned DM techniques are used in association with intelligent systems
based on artificial intelligence so that intelligent information systems can be made 1. IS are
used for using DM techniques because they act as a machine with an internet-connected
computer which has the capability to collect and analyse data for the purpose of
communication with the rest of the systems. DM techniques can be implemented while

IS FOR ANALYTICS
5
extracting knowledge from data with the help of IS in the form of neural networks. Here,
neural networks are having the capacity to adapt to changing input in a way that network
generates the optimum results without a need of re-designing the output criteria 6.
Business Intelligence (BI) using DM techniques
In this era, business intelligence can be achieved by using DM in different ways. There are so
many data processing techniques that are used in BI procedures for running them efficiently.
When BI is used for resolving the business problem, then it is known as KDD (knowledge
discovery in databases) 9. In this context, some key DM techniques are often used for the
data analysis in BI while solving business problems as follows:
 Summarization
 Anomaly detection
 Clustering
 Dependency model
 Regression 10.
Use of Data Mining in Business Analytics (BA)
DM is getting used in BA in the field of modern businesses at a large level for the purpose of
KDD. In addition to that, DM techniques offer a view of past and present conditions as well
as an understanding of the possible future outcomes that can provide effective results 8. In
this way, DM in BA acts like a detective. For instance, clusters are usually formed through
examining the current and past consumers’ behaviour such as sales selections, transactions
and service choices 10.
Applications of DM with IS
As discussed above, the neural network is the DM technique that has applications into neural
classification, Bayesian confidence propagation, radial basis function, fuzzy recurrent neural
networks, gene regulatory networks and many more 2. Apart from this, there are many
industries which are using DM techniques on a daily basis. In this context, organizations like
insurance companies, banks, hospitals, retail stores are using DM techniques for their daily
data management and KDD 5. In addition to that, some organizations are typically combining
DM with things like pattern recognition, statistics, and some other tools. It is worth knowing
that, from an application perspective, DM can be used for finding patterns as well as
connections that would otherwise be difficult to recognize. In addition, DM technology is

IS FOR ANALYTICS
6
famous and important in so many businesses as it enables firms to learn more about
customers and thereby make smart marketing decisions for future business growth.
Applications of DM techniques in real-time can be explained as below:
Company DM Application for Business Analytics
FBTO Dutch Insurance Company Marketing team predicted the overall
effectiveness of their campaigns with data
mining techniques 11.
ECtel Ltd., Israel DM reduced telecommunications fraud for
telecommunication companies all across
the world 12.
Provident Financial’s Home credit
Division, United Kingdom
Reduced customer and agent fraud
Money-saving with the help of early fraud
detection
Enhanced prosecution rate
Saved time
Shenandoah Life insurance company, US Enhanced quality of employee
performance review and underwriting
procedures 3.
Conclusion
In this way, this research has found that DM is having great importance in relation to
identifying the patterns, discovery of knowledge, forecasting, and many more within several
business domains. Apart from this, DM algorithms and techniques have been discussed such
as classification, clustering. It has been found that DM typically helps in finding the patterns
for further deciding on future trends into businesses to sustain as well as grow. Based on
findings, it can be said that DM techniques with IS have broad application domain into all
industries where the data is generated and reliable information is required. Thus, data mining
is considered one of the most important frontiers in information and database systems which
is one of the top promising interdisciplinary developments in the field of modern business
analytics.
References

IS FOR ANALYTICS
7
x
[1] J. MacLennan, Z. Tang, and B. Crivat, Data mining with Microsoft SQL server 2008.
London: John Wiley and Sons, 2011.
[2] C. S. Krishnamoorthy and S. Rajeev, Artificial intelligence and expert systems for
engineers. US: CRC Press, 2018.
[3] H. Chen, R. Chiang, and V. Storey, "Business intelligence and analytics: From big data
to big impact," MIS quaterly, vol. 36, no. 4, 2012.
[4] E. Lim, H. Chen, and G. Chen, "Business intelligence and analytics: Research
directions," ACM Transactions on Management Information systems , vol. 3, no. 4, p.
17, 2013.
[5] A. Gandomi and M. Haider, "Beyond the hype: Big data concepts, methods, and
analytics," International journal of information management, vol. 35, no. 2, pp. 137-
144, 2015.
[6] J Mark Munoz, Global Business Intelligence, 1st ed. new york: routledge, 2018.
[7] Y. Duan and J. S. Edwards, "Artificial intelligence for decision making in the era of Big
Data–evolution, challenges and research agenda.," International Journal of Information
Management, vol. 48, no. 1, pp. 63-71, 2019.
[8] P. Trkman, K. McCormack, M. De Oliveira, and M. Ladeira, "The impact of business
analytics on supply chain performance," Decision Support Systems, vol. 49, no. 3, pp.
318-327, 2010.
[9] P. Russom, "Big Data Analytics," TDWI best practices report, fourth quarter, vol. 19,
no. 4, pp. 1-34, 2011.
[10] P. Zikopoulos and C. Eaton, Understanding big data: Analytics for enterprise class
hadoop and streaming data. UK: McGraw-Hill Osbome Media, 2011.
[11] D. Delen, G. Moscato, and I. L. Toma, "The impact of real-time business intelligence
and advanced analytics on the behaviour of business decision makers.," In 2018
International Conference on Information Management and Processing (ICIMP), pp. 49-

IS FOR ANALYTICS
8
53, 2018.
[12] Clickatell. (2017) Trends in artificial intelligence technology. [Online].
https://www.clickatell.com/articles/technology/trends-artificial-intelligence-technology/
x