This study describes the rainfall-induced landslide susceptibility of Arunachal Pradesh, developed utilizing the random forest (RF) machine learning (ML) model. In this regard, various landslide conditioning factors and the importance of considering multiple conditioning factors in the mapping process are highlighted. These conditioning factors for landslides, i.e. topographic factors (slope, aspect, curvature, elevation), geologic factors (structural geology, soil type), climatic factors (precipitation) and land use land cover factors (vegetation cover, land use, human activity), are prepared from multiple sources. The RF models were trained and validated with the help of 212 historical landslide events, along with an equal number of non-landslide events, which were divided into training (70%) and validation (30%) sets. The study revealed that factors such as elevation, rainfall, slope gradient, stream power index (SPI) and land use have a significant influence on the spatial distribution of the landslides. The results of the analysis have been validated by various statistical indices such as area under curve (AUC), root mean square error (RMSE) and Kappa coefficient. The results of this study culminated in landslide susceptibility mapping (LSM) that are produced for the peak monsoon month, i.e. July. The findings offer valuable insights into the development of more efficient landslide predictive models that can be used by decision-makers and land-use managers to mitigate landslide hazards.