Micro-credit　companies　mushroomed　in　China　in　recent　years.　Those　companies　are　requiring　a　much　more　efficient　and　accurate　way　to　assess　credit　risk.　Therefore,　there　is　a　growing　trend　in　applying　machine　learning　methods　to　credit　risk　analysis　recently,　such　as　back　propagation　artificial　neural　networks　(BPANN),　support　vector　machine　(SVM)　and　etc.　These　methods　have　well　performances　but　they　are　still　lack　of　robustness　while　processing　data　with　outliers.　In　this　paper,　we　proposed　a　new　method　that　combines　random　sample　consensus　(RANSAC)　and　BPANN　which　will　help　with　dealing　data　which　includes　outliers.　For　validation,　two　real　world　credit　datasets　are　used　to　test　the　effectiveness　of　our　proposed　method.　The　findings　of　the　study　reveal　the　RANSAC-ANN　based　method　to　be　a　promising　alternative　for　credit　risk　assessment.　©,　2015,　Journal　of　Computational　Information　Systems.　All　right　reserved.