Segmentation and profiling consumers in a multi-channel environment using a combination of self-organizing maps (SOM) method, and logistic regression

With emergence of electronic trading through internet, multichannel retailing became the dominant paradigm of business world. New media emerged and a developed set of different channels were made for companies and consumers. The customers developed their experience channels from traditional purchase shops and now it is very usual for them buy from online shops, catalogues, ATMs and call centers. The main purpose of the present study is segmenting the customers regarding their tendency to different channels in information searching phases and purchase and also explaining the determining factors of their membership in this segment. Demographic and psychological variables are considered simultaneously in the present research. To this end, the data was collected through distribution of 800 questionnaires among consumers in Tehran city. Combining self-organizing maps and logistic regression was used to analyze the data. The results showed that regarding consumers’ attitude, they can be divided to four different channels including multi-channel consumers, traditional, neutral and search-oriented ones. The results also showed the existence of a multi-channel consumer section with 23.88% of the participants. Other findings showed that socio-demographic variables including gender, age, job and income level and psychological variables including innovativeness, quality consciousness, time pressure and motivation to confirm had determining roles in probable membership of consumers in different sections.