Soil erosion is one of the most important and critical processes occurring in Turkey, as in all parts of the world. It is of great importance to understand the processes that occur as soil erosion continues. The aim of this study is to determine the erosion susceptibility occurring in the Çapakçur Stream basin, one of the important erosion areas of Turkey. In the study, erosion susceptibility analysis was used using 19 conditioning factors based on 4 different methods (Shannon Entropy (SE), Logistic Regression (LR), Frequency Ratio (FR) and Weight of Evidence (WoE)), which are actively used today in erosion susceptibility analysis and determination of critical areas in terms of erosion. has been made. Model performances of the Analysis Results were evaluated based on a data set of 840 training (70%) points and 360 validation (30%) points using ROC and AUC values.. According to result of the ROC and AUC values show that Logistic regression seems to perform well on both training (AUC = 94.7%) and validating datasets (AUC = 93.5%). On the other hand, Weight of Evidence training (AUC = 93.5%) and testing datasets (AUC = 91.4%), Frequency Ratio training (AUC = 93.5%) and testing datasets (AUC = 92.4%). of the Weight of Evidence resault show that AUC and ROC values smilar to Logistic Regression result, but slightly lower than Logistic Regression. Additionally, Shannon Entropy shows that it performs lower than other methods on both training (AUC = 55.7%) and testing datasets (AUC = 56.3%). Conducting analyzes based on these methods, especially in erosion susceptibility studies, will facilitate both planning and the accuracy of the results obtained.