Landslides and slope failures are extremely unfavourable occurrences that frequently have disastrous results in many countries. The accurate prediction of slope instability is a crucial concern in geotechnical engineering. However, forecasting the instability of slopes in collapse-prone areas presents considerable challenges due to the involvement of numerous physical and geometric variables. To address this, various artificial intelligence (AI) and machine learning techniques have been employed, although their full potential has yet to be realized due to the limitations of existing algorithms. In this research, we propose an efficient machine learning approach using the Random Forest model, specifically tailored to solve the nonlinear problem discussed. We conducted an investigation, focusing on 221 cases of slopes, to assess the risk and identify its susceptibility. Our analysis revealed that the present machine model outperformed other empirical investigations in terms of the accuracy of the stability prediction. The research can aid professionals in construction and disaster management authorities by swiftly assessing slope stability for site selection in infrastructure projects. This contributes to environmental planning by supplying data for impact assessments and ensuring the safety of vital infrastructure through monitoring adjacent slopes along roads, railways, and pipelines.