Abstract: Bailong river basin is one of the four regions with high incidences of landslide and debris flow in China. Thus it is of vital importance to carry out hazard mapping of the landslides in this region to provide references for disaster management and construction planning. Using slope units as the basic assessment units, this research firstly gets the 6most contributing factors of landslides by means of principal component analysis and independence test. Then, the methods of Logistic Regression(LR) and Support Vector Machine(SVM) are conducted for landslide hazard mapping. Results show that (1) both LR and SVM can effectively evaluate the hazards of landslides in the region; (2)the SVM has a better ability in classification, predicting accuracy and model stability. According to the results of the two models, the study area are classified into five categories,i.e., very high dangerous zone, high dangerous zone, moderate dangerous zone, low dangerous zone and very low dangerous zone, taking an area proportion of 38.76%、14.48%、9.40%、11.28%、26.07% and 13.49%、21.61%、8.17%、26.70%、30.04%,respectively.