<p>Landslides pose a significant threat to the Chittagong Division of Bangladesh, particularly during the monsoon season, causing substantial socio-economic losses and fatalities. This study aims to develop a landslide susceptibility map (LSM) for the region by integrating remote sensing (RS) and geographic information system (GIS) data with advanced machine learning algorithms, specifically Gradient Boosting Machine (GBM) and Random Forest (RF). A comprehensive set of 12 conditioning factors, including elevation, slope, rainfall, and land use/land cover (LULC), was analyzed to assess landslide susceptibility. Historical landslide data from 170 locations were used to train and validate the models. Both GBM and RF models demonstrated high predictive accuracy, achieving an area under the curve (AUC) of 0.83. The KS Plot further validates the models, with the GBM model attaining KS values of 0.55 for the positive class and 0.54 for the negative class, while the RF model shows KS values of 0.54 for both classes. Comparative performance analysis revealed that the GBM model achieved 0.75 in Accuracy, 0.72 in Precision, 0.66 in Recall, and 0.69 in F1 Score. In contrast, the RF model slightly outperformed it with 0.76 in Accuracy, 0.74 in Precision, 0.67 in Recall, and 0.70 in F1 Score. These consistent improvements indicate that the RF model provides a marginally better overall performance across the evaluated metrics. The GBM model classified larger areas as very low or very high susceptibility, while RF distributed susceptibility more evenly across classes. The study highlights the effectiveness of machine learning in landslide susceptibility mapping and provides valuable insights for disaster risk management, land-use planning, and resource allocation in landslide-prone areas.</p>