To address the issues of slow convergence and large errors in existing metaheuristic algorithms when optimizing neural network-based subway passenger flow prediction, we propose the following improvements. First, we replace the random initialization method of the population in the SSA with Circle mapping to enhance its diversity and quality. Second, we introduce a hybrid mechanism combining dimensional small-hole imaging backward learning and Cauchy mutation, which improves the diversity of the individual sparrow selection of optimal positions and helps overcome the algorithm’s tendency to become trapped in local optima and premature convergence. Finally, we enhance the individual sparrow position update process by integrating a cosine strategy with an inertia weight adjustment, which improves the algorithm’s global search ability, effectively balancing global search and local exploitation, and reducing the risk of local optima and insufficient convergence precision. Based on the analysis of the correlation between different types of subway station passenger flows and weather factors, the ISSA is used to optimize the hyperparameters of the CNN-LSTM model to construct a subway passenger flow prediction model based on ISSA-CNN-LSTM. Simulation experiments were conducted using card swipe data from Harbin Metro Line 1. The results show that the ISSA provides a more accurate optimization with the average values and standard deviations of the 12 benchmark test function simulations being closer to the optimal values. The ISSA-CNN-LSTM model outperforms the SSA-CNN-LSTM, PSO-ELMAN, GA-BP, CNN-LSTM, and LSTM models in terms of error evaluation metrics such as MAE, RMSE, and MAPE, with improvements ranging from 189.8% to 374.6%, 190.9% to 389.5%, and 3.3% to 6.7%, respectively. Moreover, the ISSA-CNN-LSTM model exhibits the smallest variation in prediction errors across different types of subway stations. The ISSA demonstrates superior parameter optimization accuracy and convergence speed compared to the SSA. The ISSA-CNN-LSTM model is suitable for the precise prediction of passenger flow at different types of subway stations, providing theoretical and data support for subway station passenger density and trend forecasting, passenger organization and management, risk emergency response, and the improvement of service quality and operational safety.
