Slopes in open-pit mines are excavated to the steepest feasible angle for maximum profits, which involves a great risk of failure. Unmanned Air Vehicles (UAV) are emerging as new technology to provide information at a high spatial resolution which leads to fast and accurate qualitative results that can be used for stability analysis. The acquired images from the UAV flight plan are processed to produce Digital Elevation Model (DEM). Parameters of slope instability derived from DEM, namely slope, aspect along with inventory maps are fed as an input to Artificial Neural Network (ANN) models. ANNs have the ability to learn and generalize the knowledge on unseen data. Opencast mines in different areas are selected as training sites using random sampling. A feedforward back-propagation algorithm is implemented to analyze slope susceptibility, and the area is classified into four hazard-prone zones. Four input parameters, namely slope, aspect, drainage density and geological structures, are trained using the algorithm. The factors are rated based on the role played by each of them in causing slope failure. 20% of the training sites are selected for testing and 20% for validation purpose. Hazard-prone zones provide useful information regarding possible future which helps in drawing up measures for mitigation.