Chapter.i, " Combining Data Warehousing and Data Mining Techniques for Web Log Analysis "

In enterprises, a large volume of data has been collected and stored in data warehouses. Advances in data gathering, storage, and distribution have created a need for integrating data warehousing and data mining techniques. Mining data warehouses raises unique issues and requires special attention. Data warehousing and data mining are interrelated , and require holistic techniques from the two disciplines. The " Advanced Topics in Data Warehousing and Mining " series comes into place to address some issues related to mining data warehouses. To start this series, this volume 1, includes 12 chapters in four sections, contributed by authors and editorial board members from the International Journal of Data Warehousing and Mining. Section I, on Data Warehousing and Mining, consists of three chapters covering data mining techniques applied to data warehouse Web logs, data cubes, and high-dimensional datasets. brings together data warehousing and data mining by focusing on data that has been collected in Web server logs. This data will only be useful if high-level knowledge about user navigation patterns can be analyzed and extracted. There are several approaches to analyze Web logs. They propose a hybrid method that combines data warehouse Web log schemas and a data mining technique called Hyper Probabilistic Grammars, resulting in a fast and flexible Web log analysis. Further enhancement to this hybrid method is also outlined.