“…Earlier studies on prediction modeling have focused on the building of a single best model using statistical and artificial intelligence techniques. However, since the mid1980s, integration of multiple techniques (hybrid techniques) and, by extension, combinations of the outputs of several models (ensemble techniques) have, according to the experimental results, generally outperformed individual models (Clemen, 1989;Hansen and Salamon, 1990;Leshno and Spector, 1996;Lin and McClean, 2001;Jo and Han, 1996;Olmeda and Fernandez, 1997;Shin and Han, 1998;Lin and McClean, 2001;West et al, 2005;Chan et al, 2006;Ravi et al, 2008;Sun and Li, 2008;Verikas et al, 2010). Integration has been an integral part of the effort to reinforce the ultimate performance of knowledge-based systems by improving the performance of the prediction model.…”