Slope failures have been a critical issue in geotechnical engineering as they pose threat to human life and the environment. The analysis of slope stability method has closely followed the developments in computational methods, with the latest addition of statistical and artificial intelligence (AI) methods to assess the failure potential of slopes based on different geomaterial and geometric parameters. The AI method has advantages over the other computational methods due to spatial variability of soil, particularly during initial estimation of the stability of slope. However, professional engineers and policy planners still find it difficult to use these AI techniques due to lack of clarity and simplicity in approach. Other problems are the availability of all the parameters to assess the stability and bias of the database for stable and failed slopes. In this study a multi-objective feature selection (MOFS) algorithm has been used along with a learning algorithm Artificial neural network (ANN), a machine learning (ML) algorithm random forest (RF) has also been used to predict the instances of failed and stable slopes. The key input parameters used for the classification of slopes are unit weight of soil (γ), soil cohesion (c), internal friction angle (φ), slope angle (β), slope height (H), and pore pressure ratio (ru). Based on prediction efficacy as per confusion matrix, it was found that both of these methods (ANN + non-dominated sorting genetic algorithm (NSGA-II) and RF) proved to be more efficient than the existing AI-based methods used in the literature. The RF was found to outperform all other methods. The methods have been presented in a simpler form to assess the stability without knowing the detailed intrinsic of the algorithms and computer coding. However, these results have been obtained based on the existing dataset, which can further be improved with more comprehensive datasets. Based on the trained classification model of RF, executable software has been developed that can very efficiently classify the slope in stable and not stable classes based on the provided input parameters.