This study introduces a fuzzy filtering based technique for rendering robustness to the modelling methods. We consider a case study dealing with the development of a model for predicting the bioconcentration factor (BCF) of chemicals. The conventional neural/fuzzy BCF models, due to the involved uncertainties, may have a poor generalization performance (i.e. poor prediction performance for new chemicals). Our approach to improve the generalization performance of neural/fuzzy BCF models consists of (1) exploiting a fuzzy filter to filter out the uncertainties from the modelling problem, (2) utilizing the information about uncertainties, being provided by the fuzzy filter, for the identification of robust BCF models with an increased generalization performance. The approach has been illustrated with a data set of 511 chemicals (Dimitrov, S., Dimitrova, N., Parkerton, T., Comber, M., Bonnell, M., Mekenyan, O., 2005. Base-line model for identifying the bioaccumulation potential of chemicals. SAR and QSAR in Environmental Research 16 (6), 531-554) taking different types of neural/fuzzy modelling techniques.