This document discusses using machine learning to identify susceptible landslide areas. It describes applying the weight of evidence method to obtain susceptible areas using factors like geological conditions, terrain, and rainfall. Random forest classification with decision trees was used to analyze data from ArcGIS and R software on landslide locations from Google Earth and field surveys. The trained model calculated susceptibility for buildings in settlements and found landslide occurrence has increased in the Himalayas region over the last four decades, with high rainfall being a major triggering factor.