Autonomous Market Segments Estimation Using Density Conscious Artificial Immune System Learner

Abstract

Automated exploration of groups of customers to understand customer behavior from raw data is highly required to support strategic decision making given the pressure of competitive market. Several mathematical and statistical methods have been applied for autonomous model estimation from multivariate data. The current paper investigates employability of new generation of bio-inspired metaheuristic algorithms, named the artificial immune system (AIS), which in the current proposition, learn through density based kernels. As such the model simulates probabilistic behavior of the dendritic cells (DCs) during recognition of the antigens and danger signals, whose learning has been modeled with an infinite Gaussian mixture model. The unsupervised learning capability of the model has been found to be effective for multivariate data.