A new SOM-based method for profile generation: theory and an application in direct marketing
Authors: Alex Seret, Thomas Verbraken, Sébastien Versailles, and Bart Baesens
Appears in: European Journal of Operational Research
Keywords: Data mining, customer profiling, SOM, Direct marketing
The field of direct marketing is constantly searching for new data mining techniques in order to analyze the increasing available amount of data. Self-organizing maps (SOM) have been widely applied and discussed in the literature, since they give the possibility to reduce the complexity of a high dimensional attribute space while providing a powerful visual exploration facility. Combined with clustering techniques and the extraction of the so-called salient dimensions, it is possible for a direct marketer to gain a high level insight about a dataset of prospects. In this paper, a SOM-based profile generator is presented, consisting of a generic method leading to value-adding and business-oriented profiles for targeting individuals with predefined characteristics. Moreover, the proposed method is applied in detail to a concrete case study from the concert industry. The performance of the method is then illustrated and discussed and possible future research tracks are outlined.