F035431037

International Journal of Computational Engineering Research||Vol, 03||Issue, 5||
www.ijceronline.com ||May ||2013|| Page 31
Domain Driven Data Mining: An Efficient Solution For IT
Management Services On Issues In Ticket Processing
1,
V.R.Elangovan, 2,
Dr.E.Ramaraj
1
Research Scholar Madurai Kamarajar University Madurai,
2
Professor Department of Computer Science and Engineering Alagappa University,
1. INTRODUCTION
Information Technology (IT) can be defined as set of tools, processes, and methodologies and
associated equipment employed to collect, process and present information. In other terms, IT also includes
office automation, multimedia and telecommunications. The methodologies defined include coding,
programming, data communications, data conversion, storage and retrieval. In some companies, IT is referred
to as Management Information Services (or MIS) or simply as Information Services (or IS). The information
technology department of a large company would be responsible for storing information, protecting information,
processing the information, transmitting the information as necessary, and later retrieving information as
necessary. To perform the complex functions required in the IT field, the modern Information Technology
would use many things such as computers, servers, database management systems and cryptography. It would
also made up of several System
Administrators, Database Administrators and IT Manager. With the help of these resources, the IT Management
Services would be most efficient and powerful. The most popular IT Skills at the moment are:
Computer Networking
Information Security
IT Governance
Business Intelligence
Project Management
Information Technology Departments will be increasingly concerned with data storage and management,
and will find that information security will continue to be at the top of the list. To lead in this trend this paper
focuses the Implementation of Domain Driven Data mining in IT Management service in Order to Provide
better efficiency.
ABSTRACT
Data Mining is the new emerging technology that can be applied in many real-world problems
in order to make the solution. Conventional data mining application faces critical challenges and lack
of soft power in solving real-world complex problems when deployed. This data mining is implemented
on the IT Infrastructure in order to provide better services. In this aspect, we use a new paradigm shift
from ‘data-centered knowledge discovery’ to ‘domain-driven actionable knowledge discovery’. The
domain-driven actionable knowledge discovery also termed as Domain-Driven Data Mining, ubiquitous
intelligence must be involved and meta-synthesized into the mining process this an actionable
knowledge discovery-based problem-solving system is formed as the space for data mining. This is the
motivation and aim of developing Domain-Driven Data Mining used for IT Infrastructure Management.
In this paper, we propose a methodology to solve the problem raised in the Management of IT
Infrastructure. Also, it provides suitable solution for handling the issues raised in the ticket processing.
Thus the proposed methodology provides better services to manage the IT services and provide an
efficient way to increase the customer satisfaction.
KEYWORDS: Customer Satisfaction, Data Mining, Domain-Driven Actionable Knowledge
Discovery, IT infrastructure, Ticket Processing, Ubiquitous Intelligence.

Domain Driven Data Mining: An…
Domain Driven Design is a collection of principles and patterns that help developers craft elegant object
systems. This can lead to software abstraction called domain models. These models encapsulate complex
business logic, closing the gap between business reality and code. It is an approach to develop software for
complex needs by connecting the implementation to an evolving model. Domain is nothing but a sphere of
knowledge, influence or activity. The domain of the software is said to be the area which the user applies a
program. In this growing computerized world, data mining has emerged as one of the most essential areas in
Information Technology. Many algorithms have been proposed to focus on both domain-independent
techniques and specific domain problems. Domain-Driven Data Mining aims to develop general principles,
methodologies, and techniques for modeling and merging comprehensive domain-related factors and
synthesized ubiquitous intelligence surrounding problem domain with the data mining process, and discovering
knowledge to support business decision making. In this paper, we implement the Domain-Driven Data Mining
in IT Management services in order to reduce the work flow in the organization, and to analysis the issues
occurred in the ticket, handling the issues and then fix the issues through proper methodology. These are all
proposed in this methodology and it is experimentally verified in order to check for the efficiency of the paper.
II. RELATED WORK
Amir Mosavi et al, paper [1] described that Conventional data mining applications face serious
difficulties in solving complex real-life business decision making problems when practically deployed. This
work in order to improve the operations in a collection of business domains aims to suggest solutions by
reviewing and studying the latest methodological, technical, practical progresses and some cases studies of data
mining via domain driven data mining (DDDM). The presented paper tries to answer the question: ―what can
domain driven data mining do for real-life business applications?‖ Moreover the work attempts to provide
information and abilities to fill the existing gap between academic researches and real-world business problems.
Thomas Piton et al, paper [2] described that the trading activities of materials retail was concerned with an
extremely competitive market. However, business people are not well informed about how to proceed and what
to do during marketing activities. Data mining methods could be interesting to generate substantial profits for
decision makers and to optimize the choice of different marketing activities. In the paper, they proposed an
actionable knowledge discovery methodology, for one-to-one marketing, which allows to contact the right
customer through the right communication channel. They presented a domain-driven view of knowledge
discovery satisfying real business needs to improve the efficiency and outcome of several promotional
marketing campaigns.
Palshikar et al, paper [3], Support analytics (i.e., statistical analysis, modeling and mining of
customer/operations support tickets data) was important in service industries. In the paper, they adopted a
domain-driven data mining approach to support analytics with a focus on IT infrastructure Support (ITIS)
services. The proposed methodology can identify specific business questions and hence reduced an new
algorithms for answering them. The questions are: (1) How to reduce the overall workload? (2) How to improve
efforts spent in ticket processing? (3) How to improve compliance to service level agreements? We propose
novel formalizations of these notions and propose rigorous statistics-based algorithms for these questions. The
approach was domain-driven in the sense that the results produced are directly usable by and easy to understand
for end-users having no expertise in data-mining, do not require any experimentation and often discover novel
and non-obvious answers. All this helps in better acceptance among end-users and more active use of the results
produced. The algorithms have been implemented and have produced satisfactory results on more than 25 real-
life ITIS datasets, one of which they use for illustration.
Chengqi Zhang et al, paper [4], extant data mining were based on data-driven methodologies. The
domain-driven data mining consists of a DDID-PD framework that considers key components such as
constraint-based context, integrating domain knowledge, human-machine cooperation, in-depth mining,
actionability enhancement, and iterative refinement process. They also illustrate some examples in mining
actionable correlations in Australian Stock Exchange, which show that domain-driven data mining has potential
to improve further the actionability of patterns for practical use by industry and business.Longbing Cao, paper
[5], Traditional data mining research mainly focus]es on developing, demonstrating, and pushing the use of
specific algorithms and models. The process of data mining stops at pattern identification. Consequently, a
widely seen fact was that 1) many algorithms have been designed of which very few are repeatable and
executable in the real world, 2) often many patterns are mined but a major proportion of them are either
commonsense or of no particular interest to business, and 3) end users generally cannot easily understand and
take them over for business use. In summary, they see that the findings are not actionable, and lack soft power in
solving real-world complex problems.

To the end, domain-driven data mining (D3M) has been proposed to tackle the above issues, and
promote the paradigm shift from ―data-centered knowledge discovery‖ to ―domain-driven, actionable
knowledge delivery.‖ In D3M, ubiquitous intelligence was incorporated into the mining process and models,
and a corresponding problem-solving system was formed as the space for knowledge discovery and delivery.
Based on the related work, the paper presents an overview of driving forces, theoretical frameworks,
architectures, techniques, case studies, and open issues of D3M. We understand D3M discloses many critical
issues with no thorough and mature solutions available for now, which indicates the challenges and prospects
for the new topic.
In recent years, researchers with strong industrial engagement have realized the need to shift from ―data
mining‖ to ―knowledge discovery‖ [6], [7], [8]. Targeting real-world problem solving, knowledge discovery was
further expected to migrate into Actionable Knowledge Discovery and delivery (AKD). AKD aims to deliver
knowledge that was business friendly, and which can be taken over by business people for seamless decision
making. As a direct application of a recent research carried out by Atish et al. [9] established that there was
interaction between the classification method of data mining and domain knowledge. They concluded that the
incorporation of domain knowledge has a higher influence on performance for some data mining methods than
for others. Chien et al. [10] collaborated with domain experts to develop specific recruitment and human
resource Management strategies using data mining techniques. Their results were successfully applied in a real-
world business.
Zhao et al. examined the effects of feature construction [11] guided by domain knowledge, on
classification performance. The results of their study showed that feature construction, guided by domain
knowledge, significantly improves classifier performance. An imbalance exists between the number of data
mining algorithms published and the very few that are actually useful in a business setting. Hence conventional
data mining has failed to deliver adequate results in decision making for real life business. A need therefore
arises for a better framework within which better results can be obtained from existing data mining
methodologies, techniques, tools and applications [12].
III. PROPOSED METHOD
The aim of the paper is to propose a methodology to fix the issues raised in the ticket submitted by the
user in order to process the request, and to improve the customer satisfaction.The summary of the proposed
methodology is as follows: The IT Organization comprises of several levels of industrial patterns, to manage
and maintain the infrastructure. Each level performs its own functions depending upon the organizational
structure. Domain-Driven Data Mining extends organizational toolbox and borrows from well-known industry
patterns. Organizational patterns that the domain-driven data mining lays out are that there are solutions for
every level of detail in the system. In this paper, the IT Infrastructure management can be carried out in
Domain-Driven Data Mining in order to provide a generalized solution in any kinds of domain, that we can be
implemented. The initial step is to receive the tickets from the user to process. Upon receiving the tickets from
the user, the tickets can be classified into categories based on the concern. Since the tickets has been processed
based on these categories. Upon classifying the tickets into categories, the next step is to check for any issues or
errors arised in the submitted tickets. If so, then the issues are analyzed in order to verify whether the occurred
issues are relevant to each other. After analyzing the issues, the next process is to find the ticket with high issue
rate. The found ticket is then undergoes for the process. Then RCA is applied on the ticket.
RCA (Root Cause Analysis) is a method of problem solving that tries to identify the root causes of faults or
problems that cause operating events. The RCA is applied on the tickets with issues. The result is then
obtained and then analysis the result to get the ticket with high issue rate. The ticket with high issue rate is
identified and then analyzed the cause for the issue. Upon analyzing the cause, the next step is to verify whether
there is any option to fix the issue. If so, the next step is to apply CI on that issue.
CI (Continuous Improvement) is a method to improve the status of the tickets with issues through continuous
periodic improvement to overcome the issues. The CI can be applied on the ticket in the category, to
find the solution. The identified solution can be applied on every ticket in the category and analyze whether the
solution reduces the number of tickets causing the issue. If so, we can fix the solution to improve the customer
satisfaction by reducing the number of tickets.Thus, with the help of RCA, we can analysis the cause for the
issue and through CI, we can fix the issue and to reduce the number of tickets causing the issue. Through our
proposed methodology, we can gain more advantages which are as discussed below:

 Reduce the number of issues.
 Increase the customer satisfaction
 Increase the number of customer requirements
 No need to wait for SLA
 Efficient way to fix the issue.
Thus our proposed methodology provides a better solution to manage the issues arised in the IT field.
Diagrammatic Representation
The diagrammatic representation of the proposed methodology is given in figure 1.
Start
Get the User Tickets
Categorize the Tickets
Check for
issues
Analysis the category of
the tickets causing more
issues
Analysis the cause for
issues
Apply RCA on that
category
Apply CI for the tickets
Is there any
option to fix
the issue?
A
Yes
Yes
No
No
X

Fig.1 Representation of Proposed Method
Implementation Algorithm
Begin
Get the tickets from the user
Categorize the tickets based on the concern
For i in 1 to n categories
If issues on tickets = true then
ICat = category(i)
End if
Next
Apply RCA on ICat
Cause = Identify the root cause for the issue using RCA
If Cause possible to solve then
Apply CI on the tickets
Solution = Identify the solution using CI
End if
If Solution minimize the issue then
Apply Solution to fix the issue
End if
End
VI. EXPERIMENTAL RESULTS
The experiment is taken out in banking sector in order to verify the efficiency of our proposed method.
In that banking sector, we undergo an experiment with two sections. First, we test the result of processing the
tickets without implementing this proposed methodology. Also, each ticket is processed independently and so
the time consumption to process the ticket becomes more. Secondly, we implement proposed methodology to
verify the result. these tickets have been categorized and then it undergoes for processing. using proposed
Stop
Find solutions to fix the
error
Is the obtained
solution
reduces the
issue?
Apply the solution on the
tickets to fix the issue
A
Yes
X
Process the Tickets
No

methodology So the time consumption becomes less. Also the issues arised in the tickets has been processed
efficiently in our proposed method than the existing method. The comparison has to be made between these two
sectors and the resultant shows that the proposed method provides better solution in solving the tickets with
issues in a much better way with the help of RCA and CI methods. The comparison result is shown below:
Table.1 Comparison Data
Comparison Chart
0
20
40
60
80
100
120
1 2 3 4 5
No. of Requests
PerformanceRate(%)
No. of Tickets
Tickets with Issues
Processing Rate %(in Existing
System)
Processing Rate %(in
Proposed System)
Fig.2 Comparison Chart
From the comparison chart, it is clear that when the number of tickets and the issues increases, the
performance of the existing system becomes low compared to the proposed methodology. Thus, our proposed
system performs well in solving and processing the tickets.
VII. CONCLUSION
Thus, the proposed methodology provides an efficient solution to fix the issues raised in the tickets
through the methods RCA and CI. With the help of the proposed methodology, IT organization can process the
tickets in a much more efficient way than before. Since, we can provide the strategy to reduce the number of
tickets causing the issues, the number of customer requests has been increased. Also, there is no need to wait
for SLA to process the tickets; the customer satisfaction also gets increased. Thus, our proposed methodology
gives a better solution to manage the ticket processing in an IT organization and also to fix the issues raised in
ticket processing.
REFERENCES
[1] Adeyemi Adejuwon and Amir Mosavi, ―Domain Driven Data Mining – Application to Business‖, International Journal of
Computer Science Issues (IJCSI), Vol. 7, Issue 4, No 2, July 2010.
[2] Thomas Piton, Julien Blanchard, Henri Briand and Fabrice Guillet, ―Domain Driven Data Mining to Improve Promotional
Campaign ROI and Select Marketing Channels‖, Knowledge and Decision Team.
[3] Palshikar, G.K., ―Domain-Driven Data Mining for IT Infrastructure Support‖, IEEE International Conference on Data Mining
workshops, 2010.
[4] Longbing Cao, Chengqi Zhang, ―Domain-Driven Data Mining: A Practical Methodology‖, International Journal of Data
Warehousing & Mining, 2(4), October-December 2006.
No. of
Tickets
Tickets
with
Issues
Processing Rate
%(in Existing
System)
Processing Rate
%(in Proposed
System)
10 3 75 95
20 12 50 98
50 32 43 99
75 45 33 99
100 78 31 99.9

[5] Longbing Cao, ―Domain-Driven Data Mining: Challenges and Prospects‖, IEEE Transactions on Knowledge and Data
Engineering, Vol. 22, No. 6, June 2010.
[6] U. Fayyad and P. Smyth, ―From Data Mining to Knowledge Discovery: An Overview,‖ Advances in Knowledge Discovery and
Data Mining, U. Fayyad and P. Smyth, eds., pp. 1-34, 1996.
[7] M. Ankerst, ―Report on the SIGKDD-2002 Panel the Perfect Data Mining Tool: Interactive or Automated?‖ ACM SIGKDD
Explorations Newsletter, vol. 4, no. 2, pp. 110-111, 2002.
[8] U. Fayyad, G. Shapiro, and R. Uthurusamy, ―Summary from the KDD-03 Panel—Data Mining: The Next 10 Years,‖ ACM
SIGKDD Explorations Newsletter, vol. 5, no. 2, pp. 191-196, 2003.
[9] A. P. Sinha and H. Zhao, Incorporating domain knowledge into data mining classifiers: An application in indirect lending,
Decision Support Systems vol.46, 2008, pp.287–299.
[10] C. Chien and L. Chen, Data mining to improve personnel selection and enhance human capital: A case study in hightechnology
industry, Expert Systems with Applications, Vol. 34, 2008, pp. 280–290.
[11] H. Zhao, A. P. Sinha and W. Ge, Effects of feature construction on classification performance: An empirical study in bank failure
prediction. Expert Systems with Applications Vol. 36, 2009, pp. 2633–2644
[12] Ankerst M. Report on the SIGKDD-2002 Panel the Perfect Pata Mining Tool: Interactive or Automated? ACM SIGKDD
Explorations Newsletter, 4(2):110- 111, 2002.

F035431037

More Related Content

What's hot (17)

Viewers also liked (8)

Similar to F035431037 (20)

Recently uploaded (20)

F035431037