Automated personalisation offers a major improvement in the use of large Web sites. These systems learn from a user and suggest where on the Web site a user might move. Self-organising maps (SOM) may also be considered as a potential tool for Web data analysis. In this paper, the use of SOM analysis for automated personalisation of Internet users is demonstrated. The map was obtained by training a self-organising network with user demographics; click stream data were used to calculate the probabilities of user behaviour on the Web site. Thus, the map can be used for personalisation of users and to calculate the probabilities of each neuron in predicting where the user will next move on the Web site. The results indicate that SOM analysis can successfully process Web information.
[1]
Teuvo Kohonen,et al.
Self-Organizing Maps
,
2010
.
[2]
John Riedl,et al.
Recommender systems in e-commerce
,
1999,
EC '99.
[3]
John Riedl,et al.
Analysis of recommendation algorithms for e-commerce
,
2000,
EC '00.
[4]
M Ala-Korpela,et al.
Application of self‐organizing maps for the detection and classification of human blood plasma lipoprotein lipid profiles on the basis of 1H NMR spectroscopy data
,
1998,
NMR in biomedicine.
[5]
W El-Deredy,et al.
Application of self-organizing maps in conformational analysis of lipids.
,
2001,
Journal of the American Chemical Society.