Around the world, especially in mountainous regions, landslides are one of the most catastrophic natural disasters, capable of impacting human lives and infrastructures significantly and adversely. Assessing an area’s susceptibility with accuracy is of utmost importance for managing risks associated with disaster and supporting sustainable development, particularly in the Darjeeling district of West Bengal, India. This chapter explored the potential of advanced multi-criteria-decision-making (MCDM) such as analytic hierarchy process (AHP) and preference ranking optimization method for enrichment evaluation (PROMETHEE-II) fused with a prominent machine learning model, viz., extreme gradient boosting (XGBoost) for preparing hybrid ensembles AHP-XGBoost and PROM-XGBoost, and to conduct a comprehensive landslide susceptibility assessment. This chapter utilized a diverse dataset of geological, topographical, hydrological, and anthropogenic factors. The causative factors for landslides were selected using the Boruta algorithm. The prepared landslide susceptibility maps were validated through the area under the receiver operating characteristic (AUC-ROC) curve. The PROM-XGBoost method, with an astounding AUC-ROC score of 0.965 (training dataset) and 0.943 (testing dataset), outperformed the AHP-XGBoost model having an AUC-ROC score of 0.915 (training dataset) and 0.876 (testing dataset). The chapter not only contributes to the advancement of landslide susceptibility assessment but also provides valuable insights into the capabilities of the advanced MCDM fused with machine learning techniques and their ability to produce outcomes in a geographic environment.