An improved hybrid prediction model SSA-BP based on intelligent optimization algorithms was developed to address the complex nonlinearities and uncertainties inherent in slope displacement prediction in reservoir areas. This methodology effectively overcomes the limitations of the traditional BP networks, such as slow training speed and susceptibility to local optimum so as to improve the accuracy and robustness of slope displacement prediction. Through the global optimization of initial weights and thresholds using the Sparrow Search Algorithm (SSA), convergence and adaptability of the model was improved. The proposed model was trained using five-month real-time displacement monitoring data obtained from the Zhangjiawan slope. A comparative performance analysis was conducted between the SSA-BP model and BP networks optimized by genetic algorithm (GA) and particle swarm optimization (PSO). The results demonstrate that the SSA-BP model achieves rapid convergence within 24 iterations, significantly outperforming the comparative models. Evaluation metrics including root mean square error, mean absolute percentage error , and coefficient of determination (R²) reveal superior performance of the SSA-BP model. This research presents a reliable and efficient intelligent approach for accurate and robust slope displacement prediction in reservoir area.