Check dams are considered to be one of the most effective measures for conservation of the soil and water resources. However, identifying the most suitable sites for the installation of check dams remain quite demanding. This research investigates and compares five machine learning algorithms (MLAs) - boosted regression trees (BRT), multivariate adaptive regression spline (MARS), mixture discriminant analysis (MDA), random forest (RF), and support vector machine (SVM) - for generating check-dam site-suitability maps (CDSSMs) and assessing them in Firuzkuh County, Iran. First, the locations of 475 existing check dams were monitored, registered, and divided into calibration (70%) and testing datasets (30%) for training and validation of the models. Fourteen check-dam conditioning factors (CDCFs) were selected and checked for multicollinearity. The relative importance of the CDCFs assessed using the elastic net (ENET) algorithm. Results demonstrated that distance from river (DFR) and drainage density (DD) to be the most significant factors for mapping the suitable sites for the erection of check dams. This research revealed that all of five MLAs had excellent accuracy for predicting the check-dam site-suitability with high AUC values: RF (0.966), SVM (0.878), MARS (0.878), MDA (0.844), and BRT (0.843). The most accurate model (RF) showed that 16.95%, 35.55%, 31.08%, and 16.42% of study area comes under low, moderate, high, and very high suitability classes. The outcome achieved by this research will be helpful to sustainability planners and managers in constructing check dams at suitable sites for better conservation of soil and water resources.