Web Personalization Using Usage Based Clustering In today’s internet environment it is more difficult to access the relevant information from the web. Because www is a vast data warehouse of web pages and links .On internet huge amount of information is available which are approximately 1 millions of pages are added day to day. To get the “right” information from such warehouse to the user and to avoid website exploration web personalization get needed. It is the life blood of web usages mining and e-learning process to improve the system and its design as per the user’s interest. It acts as a tool to avoid the content over loading on websites for effective web navigation. Here we present web personalization which introduces web mining that is application of a data mining.

1. International Journal of Advanced Research in Technology, Engineering and Science (A Bimonthly Open Access Online Journal)
Volume1, Issue3, Nov-Dec, 2014 .ISSN: 2349-7173(Online)
International Journal of Advanced Research in Technology, Engineering and Science (A Bimonthly
Open Access Online Journal) Volume1, Issue3, Nov-Dec, 2014 .ISSN: 2349-7173(Online).
Research/Review Paper: Web Personalization
Using Usage Based Clustering
Author: Madhavi M.Mali ,Sonal S.Jogdand , Deepali P. Shinde
Paper ID: V1-I3-002
Visit: www.ijartes.org
Copyright to IJARTES

2. International Journal of Advanced Research in Technology, Engineering and Science (A Bimonthly Open Access Online Journal)
Volume1, Issue3, Nov-Dec, 2014 .ISSN: 2349-7173(Online)
All Rights Reserved©2014 IJARTES Visit: www.ijartes.org Page 7
Web Personalization Using Usage Based Clustering
Madhavi M.Mali 1
, Sonal S.Jogdand2
, Deepali P. Shinde3
____________________________________
ABSTRACT
In today’s internet environment it is more difficult to
access the relevant information from the web. Because
www is a vast data warehouse of web pages and links .On
internet huge amount of information is available which
are approximately 1 millions of pages are added day to
day. To get the “right” information from such warehouse
to the user and to avoid website exploration web
personalization get needed. It is the life blood of web
usages mining and e-learning process to improve the
system and its design as per the user’s interest. It acts as
a tool to avoid the content over loading on websites for
effective web navigation. Here we present web
personalization which introduces web mining that is
application of a data mining.
____________________________________________
Keywords: Data mining, web mining, web usage mining,
personalization.
____________________________________________
1. INTRODUCTION
Today’s world is ‘Information Age’ due to information
globalization and technology, www is a powerful tool to
store, retrieve and propagate the information as per the
user’s need. To improve on click search on a particular
website, it is necessary for web developer to use web
personalization. In [1] Web Personalization is simply
defined as the task of making Web-based information
systems adaptive to the needs and interests of individual
users. Typically a personalized websites fulfills the user’s
aspectives by collecting information about their
preferences and adopts its services to increase ratio of
human computer interaction. We describe the process of
personalization in terms of an application of a data mining
to the collected web data. Web personalization is the
science of improving navigation result of visitor’s
requirement by extracting statistical information and
discovering interesting usage patterns of visitors using
clustering algorithms.
_______________________________________________
First Author Name: Madhavi M.Mali, Pimpri Chinchwad Polytechnic,
Pradhikaran Nigdi Pune.
Second Author Name: Sonal S.Jogdand, Pimpri Chinchwad Polytechnic,
Pradhikaran Nigdi Pune.
Third Author Name: Deepali P. Shinde, Pimpri Chinchwad Polytechnic,
Pradhikaran Nigdi Pune.
_______________________________________________
To discover usage patterns web personalization uses a tool
called web mining. Web mining is advanced research area
in web personalization. Web mining examines the use of
data mining on the World Wide Web. Web mining is the
application data mining techniques on the web to discover
interesting patterns. The website contents are customized
as per user preferences and frequent access. The pages
which are accessed frequently by the user are monitored to
provide customized view of the website to the user.
DATA MINING
The application of data mining techniques depends on data
types: Web content mining, web structure mining, and web
usage mining.
2. WEB MINING
Web mining is a data mining technique of exploring the
information from the web as per user usage. Web mining is
classified into following types:
2.1 Web content mining
Web content mining is a process of analyzing the content
of web pages. It is used to identifying the most frequently
accessed information. It allows scanning of entire web to
retrieve needed information from clustered pages and
provide the same to search engines. Web content mining
also helps to give high quality results to the uses when
required to search engines. Due to this it increases the
productivity because of direct use of content mining of text
and visuals.
2.2 Web structure mining
Web structure mining deals with linking of different web
pages which might be static or dynamic [12]. The linking
is through XML tags and hyperlinks.
2.3 Web usage Mining
WUM is a technique of identifying user preferences within
a particular site. Depending on user access patterns i.e.
which information the user access or search frequently, the
user choices are identified. This is done through page
references and session information of the user. Information
is also collected from web server and application server
tags. The patterns collected through WUM helps to
understand the visitor’s preferences. It also helps to
organize the site efficiently and create a personalized view
of the page or site to the user. Typical data sources for web
usage mining are web structure data, web content data,
user profile and weblog.

3. International Journal of Advanced Research in Technology, Engineering and Science (A Bimonthly Open Access Online
Journal) Volume1, Issue3, Nov-Dec, 2014 .ISSN: 2349-7173(Online)
All Rights Reserved©2014 IJARTES Visit: www.ijartes.org Page 8
Fig. for WUM
3. WEB USAGE MINING AND
PERSONILIZATION
For realizing the more personalized, user friendly and
business web services the essential tool used is Web usage
mining. As we discuss above to avoid surplus of
information on website web personalization is used. By
using web usage mining based on web personalization we
are able to identify needs and preferences of each user
about web nevigation.WUM is the process of discovering
and interpreting patterns of user access to web systems by
digging the data collected from the user and machine
interactions.
Typically WUM system based on 4 layers:
1. Data Collection/Tracking - In which user interactions
are captured and acquired. In data collection phase, the
data is collected from the web servers and from the
information sent by the client. Packet which is sent across
the network is also monitored. This data collection is used
for personalization.
2. Data Preprocessing- In this phase, we find out from
where the data is received. This information is collected
from the session information. Techniques are used to filter
the data and use it in the next stage.
3. Pattern Discovery- The discovered patterns are usually
represented as collections of pages, objects, or resources
that are frequently accessed by groups of users with
common interests. To determine the effective marketing
strategies and optimizing the logical structure of the
website analyzing of the users, how website is accessed is
critical. According to the patterns required for web
personalization which corresponds to the interests of the
user. At this stage by applying the learning methods we
insist the construction of user models.
4. Knowledge Post Processing: This is the last phase
where extracted data is evaluated and represent in the
human understandable forms such as reports and visual
techniques.
4. PERSONILIZATION
Personalization who stores, collects, combines the
information from transaction of sites, scrutinize the
information and according to the result it produces the
information for people who visit the website. Any action
that adapts information or services provided by a website
to the needs of user by taking advantage of the knowledge
gained from the user’s navigational behavior is web
personalization. Web personalization’s techniques are used
by websites to send customize advertisements to the
customers and recommendation of different products. It is
used largely in marketing tactics to increase the e-
commerce business.
Web personalization can be done in the following
methods:
1. Implicit:-Implicit personalization will be performed by
system or web page based on the user behavior on the web.
2. Explicit:-User will be able to modify the system using
the feature provided by the system itself.
3. Hybrid:-It is a combination of both implicit and
explicit. A Web personalization system can offer a variety
of functions. The personalization functions are:
memorization, guidance, customization and task
performance support [13]. Each of these is examined in
more detail below.
Memorization: This is the simplest form of
personalization method where the system records and
stores information about the user in its memory. For
example name and browsing history. The past history of
the user is displayed without the further processing
whenever the user returns to the site. Memorization is
offered as complete personalization solution rather than a
standalone function.
Guidance: - It refers to make an effort to assist the user in
getting the information the user is in search of and also
provide the user with alternative browsing options.
Customization:-It refers to modification of web page in
terms of content, structure and layout in order to
understand user’s knowledge, preferences and interests.
The main purpose is the management of information load
for easy interaction of the user with the site.
Task Performance Support:-
Task performance support is a client side personalization
system which acts on behalf of the user. It is very similar

4. International Journal of Advanced Research in Technology, Engineering and Science (A Bimonthly Open Access Online
Journal) Volume1, Issue3, Nov-Dec, 2014 .ISSN: 2349-7173(Online)
All Rights Reserved©2014 IJARTES Visit: www.ijartes.org Page 9
to the adaptive learning systems used in educational
models.
5. APPROACHES TO WEB PERSONALIZATION
During the evolution of the web, personalization has been
recognized as a remedy to the information overload
problem and as a means of increasing visitor loyalty to a
Web site. Considering the importance of web
personalization for customizes services following are the
approaches in brief:
(a)Manual decision rule systems- In this approach the
designers design the web contents through different user
model. Two examples from a wide range of products that
adopt this approach are Yahoo!’s personalization engine
and web sphere Personalization (IBM).
(b) Content-based filtering systems- In this approach the
users browsing patterns are analyzed and accordingly
different filtering systems are used. The personal
preferences of the user are taken into consideration when
the page is shown to him next time. These models can be
used to filter news items according to each user’s
requirements.
(c) Social or collaborative filtering systems- In this
approach, a particular service of the website is
personalized taken into consideration the ratings and the
statistics information obtained from customer browsing.
Most commonly used in amazon.com electronic shop. The
Recommendation Engine (Net Perceptions) and web
sphere personalization (IBM) are examples of products
that use also this method.
Fig 1: Web usage mining process
6. CONCLUSION AND FUTURE DIRECTIONS
Analysis of business goals, development of business
requirements, use cases and metrics are required by
personalization. If this is done properly using
personalization will not be a difficult task for
organizations to increase their business throughput.
7. ACKNOWLEDGMENTS
We express our gratitude towards the experts who have
contributed in the development of subject herein.
REFERENCES
[1] Web Usage Mining and Personalization Bamshad Mobasher,
DePaul University
[2] Analysis of Web Usage Mining Hui Yu, Zhongmin Lu School
of Management, South –Central University for Nationalities,
Wuhan, P.R.China
[3] Intelligent Techniques for Web Personalization Sarabjot Singh
Anand and Bamshad Mobasher
[4] Web Mining – Accomplishments & Future Directions Jaideep
Srivastava, Prasanna Desikan, Vipin Kumar
[5] Web Mining by Juan C. Dürsteler
[6] Efficient and Anonymous Web-Usage Mining for Web
Personalization Cyrus Shahabi, Farnoush Banaei-Kashani
[7] Web site personalization IBM developer works

5. International Journal of Advanced Research in Technology, Engineering and Science (A Bimonthly Open Access Online
Journal) Volume1, Issue3, Nov-Dec, 2014 .ISSN: 2349-7173(Online)
All Rights Reserved©2014 IJARTES Visit: www.ijartes.org Page 10
[8] Web Usage Mining & Personalization Dr. Guandong Xu,
[9] Intelligent Web & Information Systems (IWIS) Department of
Computer Science, Aalborg University
[10] A Conceptual Model for Website Personalization and Web
Personalization Kavita Das and O.P. Vyas
[11] Intelligent Techniques for Web Personalization Sarabjot Singh
Anand and Bamshad Mobasher
[12] How to Win Online: Advanced Personalization in E-Commerce
An Oracle White Paper March 2011
[13] A Near Real-Time Personalization for eCommerce Platform
Amit Rustagi
[14] Web Usage Mining as a Tool for Personalization: A Survey
Dimitrios Pierrakos, Georgios paliouras, Christos
Papatheodorou and Constantine D. Spyropoulos
[15] R. Cooley, B. Mobasher, and J. Srivastava. Data Preparation for
Mining World Wide Web Browsing Patterns. Journal of
Knowledge and Information Systems, 1(1):5–32, 1999.
[16] J. Srivastava, R. Cooley, M. Deshpande, and P. Tan. Web Usage
Mining: Discovery and Applications of Usage Patterns from
Web Data. SIGKDD Explorations, 1(2):12–23, 2000
[17] Web usage mining: Discovery and applications of usage patterns
from web data. Jaideep Srivastava, Robert Cooley, Mukund
Deshpande, and Pang-Ning Tan SIGKDD Explorations,
1(2):12–23, 2000.
[18] WebMining,http://www.galeas.de/webmining.html.