The main purpose of this study was to compare the performance of Support Vector Machines (SVM), Stochastic Gradient Descent (SGD), and Bayesian Logistic Regression (BLR) algorithms for landslide susceptibility modeling in the Yozidar-Degaga region, Iran. Initially, a distribution map with 175 landslides and 175 non-landslide locations was prepared and the data were classified into a ratio of 80% and 20% for training and model validation, respectively. Based on Information Gain Ratio (IGR) technique, 13 derived factors from topographic data, land cover and rainfall were selected for modeling. Then, the SVM, SGD, and BLR algorithms were selected based on size of the data and required accuracy of the output, to learn and prepare landslide susceptibility maps. Statistical criteria were employed to evaluate the models for both training and validation datasets. Finally, the performance of these models was evaluated by the area under the receiver operating curve (AUC). The results showed that SVM algorithm (AUC = 0.920) performed better than SGD (AUC = 0.918) and BLR (AUC = 0.918) algorithms. Therefore, the SVM model can be suggested as a useful tool for better management of landslide-affected areas in the study area. In this study, all three models (SVM, SGD and BLR) were implemented in WEKA 3.6.9 software environment to prepare landslide susceptibility maps.
