2. Web Log Mining and Parallel SQL Based Execution
1]Masaru Kitsuregawa
, Takahiko Shintani5
, Takeshi Yoshizawa5
and Iko Pramudiono5 
| (5) |
Institute of Industrial Science, The University of Tokyo, 7-22-1 Roppongi Minato-ku, 106 Tokyo, Japan |
Abstract
We performed association rule mining and sequence pattern mining against the access log which was accumulated at NTT Software
Mobile Info Search portal site. Detail web log mining process and the rules we derived are reported in this paper. The integration
of web data and relational database enables better management of web data. Some researches have even tried to implement applications
such as web mining with SQL. Commercial RDBMSs support parallel execution of SQL. Parallelism is key to improve the performance.
We showed that commercial RDBMS can achieve substantial speed up for web mining.
IBM Japan Co.,Ltd. 1-1, Nakase, Mihama-ku, Chiba-shi, Chiba 261-8522, Japan
References secured to subscribers.