Slope stability analysis is a complex system engineering problem. Based on the principles of Bayes discriminating analysis(BDA) theory and the actual characteristics of the project, the Bayes discriminating analysis model to predict slope stability was established to predict slope stability. Six indexes, i.e., unit weight, cohesion force, internal friction angle, slope angle, slope height, and pore pressure ratio were used as discriminant factors to establish a discriminant analysis model for slope stability forecast. Bayes discriminant functions obtained through training 32 measured data of slope were employed to compute the Bayes function values of the evaluating samples. The cross-validation method was introduced to verify the stability of BDA model and the ratio of mistake-discrimination was low after the BDA model was trained. Seven data in the slope engineering were used to test the discriminant ability of BDA model, the maximal function value was used to judge which population the evaluating sample belongs to. The results showed that the prediction results are identical with actual situation, and consistent with the support vector machine model, which prove that the BDA model has good classifying performance, high prediction accuracy and low misdiscrimination rate and can be used in practical engineering.
