Gene　selection　prior　to　classification　has　been　an　important　topic　in　bioinformatics,　since　last　decade.　Small　sample　size　and　high　dimensionality　in　microarray　data　pose　great　challenges　for　performing　efficient　classification.　In　this　paper　we　propose　efficient　hybrid　method　(GT-kernelPLS)　with　a　combination　of　wrapper　like　technique　coalitional　game　theory　and　kernel　partial　least　square　(kernelPLS)　filter　method.　Experimental　results　on　ten　microarray　data　sets　ensure　that　GT-kernelPLS　achieve　higher　accuracy　than　several　state　of　the　art　feature　selection　methods,　and　it　exhibits　a　reasonable　execution　time,　even　for　the　data　sets　having　more　than　twenty　thousand　genes.