A hybrid intelligent approach for modeling brand choice and constructing a market response simulator

Brand choice models, used for describing the process of choosing mutually exclusive alternatives, attracted a large amount of attention from researchers in the early of the recent decade. These models can be used as a market response simulator for simulating marketing strategies and assessing how changes in marketing variables such as pricing and promotions will influence consumer behavior and thus perform ‘what-if’ simulations. So a reliable and relevant brand choice model can be very useful and effective, which, in fact, represents a worthwhile opportunity to improve the efficiency of the marketing decisions. In this paper we offer a new approach by integrating of Probabilistic Neural Network (PNN) and Data preprocessing for brand choice modeling and constructing a market response simulator. This approach, called Preprocessed-Probabilistic Neural Network (PPNN), consists of two main stages. First, a robust Genetic Based Instance Selection Model (GBIS) employed to look for a representative data subset of instances in training data set. The second stage ends up with a relevant brand choice model, using a probabilistic neural network trained by Dynamic Decay Adjustment Algorithm (DDA). The evaluation process is carried out using the same data set been used in literature for modeling individual consumer choices in a retail coffee market. The evaluation results show that the offered approach outperforms all previous methods, so it can be considered as an effective tool for consumer behavior modeling and simulation.