An experimental comparative study of web mining methods for recommender systems
DIWED'06 Proceedings of the 6th WSEAS International Conference on Distance Learning and Web Engineering
Service-mining based on knowledge and customer databases
KSEM'07 Proceedings of the 2nd international conference on Knowledge science, engineering and management
Identifying user preferences with Wrapper-based Decision Trees
Expert Systems with Applications: An International Journal
Hi-index | 0.01 |
In this paper we present a simple classification systemfor predicting user behavior when browsing a web site devoted to inform about university degrees. More than building a very accurate classifier, we want to study which kind ofcombination scheme performs better in front of a complexity constraint. A set of marks embedded in the web pagesbeing visited by each user is used as the input for a classification system which decides whether the user will be interested in accessing other related parts of the web site or not.We compare two different classification systems: the firstone is built using decision trees for the whole data set, withthe aim of studying user profiles and variable importance,while the second one combines simple classifiers based onsmall decision trees using a combination of the voting andcascading paradigms, in order to make predictions whichevolve during the period of time the web site is collectingdata. Results show that it is possible to extract useful information for studying user profiles and for predicting userbehavior using small decision trees.