Deployment of the Microeconomic Consumer Theory in the Artificial Neural Networks Modelling: Case of Organic Food Consumption

Organic food consumption has become a significant trend in consumer behaviour, determined by various motives, among which the price does not play major role, thus reflecting Lancaster approach to microeconomic theory. Additionally, artificial neural networks (ANNs) have proven potential providing accurate and efficient models for predicting behaviour. Considering these two trends, this study aims deploy emerging area of intelligence. The paper develop ANN-based predictive model investigate relationship between organic consumption, demographic characteristics, health awareness attitudes. Survey research been conducted on sample Croatian inhabitants, ANN used assess importance determinants consumption. A Three-layer Multilayer Perceptron Neural Networks (MLPNN) structure constructed validated select optimal number neurons transfer functions. One layer is as first input, while other are hidden layers (the covers radially symmetrical sigmoid function; second output, softmax function). Three versions testing, training, holdout data structures were ANNs. highest accuracy was achieved with 7-2-1 partition. best that showing smallest percent incorrect predictions stage, second-lowest cross-entropy error, correct classification rate, under ROC curve. results show availability healthy shops strongly impacts Using methodology, analysis confirmed validity approach, stating characteristics or attributes goods defined product itself.