ORIGINAL PAPER Using fuzzy logic modelling to simulate farmers ’ decision-making on diversification and integration in the Mekong Delta, Vietnam

The Author(s) 2010. This article is published with open access at Springerlink.com Abstract To reveal farmers ’ motives for on-farm diver-sification and integration of farming components in the Mekong Delta, Vietnam, we developed a fuzzy logic model (FLM) using a 10-step approach. Farmers ’ decision-mak-ing was mimicked in a three-layer hierarchical architecture of fuzzy inference systems, using data of 72 farms. The model includes three variables for family motives of diversification, six variables related to component inte-gration, next to variables for the production factors and for farmers ’ appreciation of market prices and know-how on 10 components. To obtain a good classification rate of the less frequent activities, additional individual fine-tuning was necessary after general model calibration. To obtain the desired degree of sensitivity to each variable, it was necessary to use up to five linguistic values for some of the input and output variables in the intermediate hierarchical layers. Model’s sensitivity to motivational variables determining diversification and integration was of the same magnitude as its sensitivity to market prices and farmers’ know-how of the activities, but less than its sensitivity to labour, capital and land endowment. Modelling to support strategic decision-making seems too elaborate for individ-ual farms, but FLM will be useful to integrate farmers’ opinions in strategic decision-making at higher hierarchical levels