Ecological niche modelling is a method to predict presence of a given biological species by environmental parameters. It is also applicable to humans as eco-cultural niche modelling (ECNM) under the condition that the human behaviour significantly depends on the natural environment . There are two methods of ECNM--Genetic Algorithm for Rule-set Production (GARP)  and Maximum Entropy Model (Maxent) . Both models require geocoordinates of archaeological sites and environmental variables such as terrain elevation, slope, mean temperature, and annual precipitation. GARP outputs prediction in binary [0,1], while Maxent outputs in continuous probability [0...1]. This paper applies these predictive models to two case studies: 1) the replacement of Neanderthals by anatomically modern humans in the Levant, and 2) the subsistence economy of Jomon hunter-gatherer-fishers in East Japan. Then validity of the models is discussed and a hybrid model based on the two models is proposed for better predicting and visualising site presence.  Banks, W. E. et al. 2008. Human ecological niches and ranges during the LGM in Europe derived from an application of eco-cultural niche modeling. Journal of Archaeological Science 35:481-491.  Stockwell, D. R. B. 1999. Genetic Algorithms II: spatial distribution modelling. In: Machine Learning Methods for Ecological Applications, edited by A. H. Fielding, Kluwer, pp. 123-144.  Phillips, S. J. et al. 2006. Maximum entropy modeling of species geographic distributions. Ecological Modelling 190:231-259.