Landslides are natural disasters that cause a lot of financial and life losses in the country, annually. Identifying high risk areas can reduce the damages and be effective on land development policies. The aim of this study was to spatial prediction of landslide hazard in Sanandaj-Kamyaran main road in Kurdistan province. In current study, landslide hazard mapping were performed using advanced data mining algorithms including weights of evidence (WOE), and evidential belief function (EBF). Firstly, 79 landslides location were obtained from field surveys. Then, these landslides were randomly categorized into two groups of training (70%, 55 locations) and validation (30%, 24 locations). In the current study according to previous studies and geography conditions, fourteen conditioning factors including slope, aspect, curvature, elevation, distance to fault, lithology, SPI, TWI, soil type, density of river, normalized difference vegetation index (NDVI), distance to river, distance to road, the slope angle, and land use were determined to landslide hazard potential mapping. Also, in this research, the receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used for validation of the two achieved landslide susceptibility maps. The AUC results introduced the success rates of 0. 89 and 0. 79 for WOE and EBF, respectively. Therefore, WOE model, having the highest AUC, was the most accurate method for spatial prediction of landslide hazard in the study area. In addition, the results of the study showed that advanced data mining algorithms based on their structure have sufficient accuracy to spatial prediction of landslide in the study area.