Neural network-based sensitivity analysis has emerged as a critical tool for evaluating parameters in geotechnical engineering systems, particularly in assessing soil slope stability. Artificial neural networks (ANNs), a class of soft computing techniques, excel at modeling nonlinear dynamic behaviors inherent to geotechnical systems, enabling robust predictions and risk evaluations. Apart from stability assessment sensitivity of slope stability parameters can also be assessed. However, ANN requires huge training data for its development. In this study, the stability of a large number of slopes is assessed using GeoStudio’s Slope/W software, and this solved data is used for ANN training. After developing the ANN model, sensitivity of each of the slope parameters is assessed. Various parameters consider for slope stability assessment are strength parameters (cohesion and angle of internal friction), geometric parameters (height of the slope and slope inclination), pore water pressure, and unit weight of soil. Out of all these parameters, most sensitively influenced parameter was identified in this study.