<p>In response to the problems of slow convergence speed and overfitting in current machine learning models for slope stability prediction, this paper proposes a Global Search Whale Optimization Algorithm (GSWOA) based on a global search strategy to optimize the slope stability prediction model of the Kernel Extreme Learning Machine (KELM). Six parameters were selected as slope stability prediction indicators, including slope height (<i>H</i>), slope angle (<i>β</i>), unit weight (<i>γ</i>), cohesion (<i>c</i>), internal friction angle (<i>φ</i>) and pore water pressure ratio (<i>r</i>_u). By collecting slope stability sample data from multiple literature sources, a slope stability prediction database containing 167 sets of slope engineering cases was established. Three global search strategies were introduced to optimize the Whale Optimization Algorithm (WOA), including adaptive weighting, variable spiral strategy, and optimal neighborhood perturbation strategy, the Extreme Learning Machine (ELM) was improved by kernel function, the GSWOA-KELM model for slope stability prediction was constructed. Comparing the model proposed in this paper with the unimproved WOA-KELM model, the results show that the testing set accuracy, precision, recall, and F1-score are 88.00%, 92.55%, 96.39%, and 0.9328, respectively, which are all superior to the compared model. The GSWOA-KELM model was applied to a construction project slope for verification, and the predicted results were completely consistent with the actual working conditions, indicating that the research results in this paper have certain guiding significance and application value for slope stability prediction.</p>