Intranet
LANC 2009
Lanc2007
Industrial Informatics Research Group

Referrer Graph: a low-cost web prediction algorithm

B. de la Ossa , A. Pont , J. Sahuquillo , J.A Gil ,
Proceedings of the 25th ACM Symposium On Applied Computing (ACM SAC 2010)
2010

Abstract

This paper presents the Referrer Graph (RG) web prediction algorithm as a low-cost solution to predict next web user accesses. RG is aimed at being used in a real web system with prefetching capabilities without degrading its performance. The algorithm learns from user accesses and builds a Markov model. These kinds kind of algorithms use the sequence of the user accesses to make predictions. Unlike previous Markov model based proposals, the RG algorithm differentiates dependencies in objects of the same page from objects of different pages by using the object URI and referrer in each request. This permits us to build a simple data structure that is easier to handle and, consequently, with a lower computational cost in comparison with other algorithms. The RG algorithm has been evaluated and compared with the best prediction algorithms proposed in the open literature, and the results show that it achieves similar precision values and page latency savings but requiring much less computational and memory resources.

Download

© Copyright Material:
Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the publisher.

It is understood that all persons copying this information will adhere to the terms and constraints invoked by the copyright holder.
[Download PDF]

BibTex

@inproceedings{de:2010,
Author = {de B., Pont A., Sahuquillo J., Gil J.A, },
title = {Referrer Graph: a low-cost web prediction algorithm},
booktitle = {Proceedings of the 25th ACM Symposium On Applied Computing (ACM SAC 2010)},
pages = {},
year = {2010},
isbn = {},
publisher = {ACM}
}
Valid XHTML 1.1 ¡CSS Válido! Get Firefox!