Abstract—Nanotechnology is the process that develops novel materials at size of 100 nm or less and has become one of the most promising areas of human endeavor. Because of their intrinsic properties, nano-particles are commonly employed in electronics, photovoltaic, catalysis, environmental and space engineering, cosmetic industry and even in medicine and pharmacy. However, recent toxicological studies have shown evident toxicity of some nano-particles to living organisms (toxicity), and their potentially negative impact on environmental ecosystems (ecotoxicity). Characterization is the connection between an abstract material model and its real world behavior. Until recently, relatively simple testing procedures are available for the characterization of engineering materials. However, the large number of nanoparticles and the variety of their characteristics including sizes and coatings show that it is only rational to develop an approach that avoids testing every single nanoparticle produced. The modeling of the material is becoming increasingly difficult and complex such that it requires the use of complex numerical models. A trend is being established where characterization is accomplished through a combination of numerical modeling and experimental testing. Several researchers have carried out analytical and numerical studies on modeling of materials but failed to give a simple model to predict the physico-chemical properties of nano-materials. Computational intelligent techniques such as artificial neural network (ANN), fuzzy logic, genetic algorithm and support vector machine (SVM) are successfully used to solve complex problems. In this paper, a hybrid genetic algorithm tuned support vector machine classifier (GA-SVMC) model is developed to predict the toxicity of nano-materials.