Abstract: The relationship between slope stability and influencing factors is complex and nonlinear. Support vector machine (SVM) is used to build the nonlinear relationship. The parameters of SVM are optimized with a continuous ant colony algorithm (CACA). Thus the ACAC-SVM is proposed for forecasting slope stability. Slope of right-bank spandrel groove at Jinping is forward slope. A majority of the slope surface is bare and comprised of bedrock. the natural slope is comprised of marbleand stability now. The CACA-SVM is used to analysis the stability of the slope of right-bank spandrel groove at Jinping. The results are in good agreement with the actual data, which indicates that the CACA-SVM can be well applied to the analysis of slope stability