Abstract
The Web Mining is the collection of
methods of Data Mining used to extract
constructive knowledge and useful information
from Web data. As many organizations depend on
the Internet to carry out daily trade, the study of
Web mining methods to find out useful
information has become increasingly significant.
In Web Mining, it is required to have a predictive
and productive association rules for web
navigation. An association rule expresses an
association between items or sets of items.
Discovering these rules is important for cross
marketing analysis, attached mailing applications,
store layout, customer segmentation based on
buying patterns etc. One of the significant
challenges to offer web intelligent services is the
analysis of web server logs. This paper introduces
the user navigation approach dependent on their
actions discovered from web log information and
also it offers better prediction correctness than
Streaming Association Rule (SAR) model. It
improves the present SAR mining pattern with
Apriori-like algorithm and Dynamic
programming approach. To recognize and better
serve the requirements of web based functions,
web usage mining act as a basic driving force.
Web usage mining has become admired in various
areas related with Web site expansion. In Web
usage mining, frequently visited navigational
paths are taken out in terms of Web page
addresses from the Web server visit logs, and the
patterns are used in various applications including
recommendation.