A Weighted SOM for Classifying Data with Instance-Varying Importance
Peter Sarlin · 2012
This paper presents a Weighted Self-Organizing Map (WSOM). The WSOM combines the advantages of the standard SOM paradigm with learning that accounts for instance-varying importance. While the learning of the classical batch SOM weights data by a neighborhood function, we augment it with a user-specified instance-specific importance weight for cost-sensitive classification. By focusing on instance-specific importance to the learning of a SOM, we take a perspective that goes beyond the common approach of incorporating a cost matrix into the objective function of a classifier. When setting the weight to be the importance of an instance for forming clusters, the WSOM may also be seen as an alternative for cost-sensitive unsupervised clustering. We compare the WSOM with a classical SOM and logit analysis in financial crisis prediction. The performance of the WSOM in the financial setting is confirmed by superior cost-sensitive classification performance.