Improving Infoville XXI using Machine Learning Techniques
published: Feb. 25, 2007, recorded: July 2005, views: 2865
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Infoville XXI is a citizen web portal of Valencia (Spain). This paper presents several approaches based on Machine Learning that help in improving the site. Three ways of improvement are taken into account: (i) user clickstream forecasting, (ii) user profiling by clustering and (iii) recommendation of services to users, being the last two techniques part of a methodological framework with general applicability that tries to be useful for a range of web sites as wide as possible. Results obtained with data sets from this web portal show that the most appropriate techniques for user clickstream forecasting become Support Vector Machines and Multilayer Perceptrons, whilst Adaptive Resonance Theory and Self-Organizing Maps appear to be the most suitable techniques for clustering. Final recommendation and adaptation of the recommender system is currently being developed by using Learning Vector Quantization and Reinforcement Learning.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !