Features　selection　is　a　process　to　find　the　optimal　subset　of　features　that　satisfy　certain　criteria.　The　aim　of　feature　selection　is　to　remove　unnecessary　features　to　the　target　concept.　This　paper　investigates　some　basic　concepts　of　rough　set　theory　and　ant　colony　optimization.　Based　on　these　studies,　a　hybrid　approach　to　feature　selection　on　combination　of　ant　colony　optimization　and　rough　set　theory　is　proposed　Experimental　results　obtained　show　this　hybrid　approach　is　a　promising　method　for　feature　selection.