A prediction model for spiking neural network based on cuckoo search algorithm（ CS-SNN） is proposed to solve the problem of inaccurate bus arrival time and the difference of working characteristics between working days and weekends. By analyzing and verifying the performance characteristics of the spiking neural network（ SNN）

the cuckoo algorithm with better optimization performance is used to optimize the initial parameters of the Spiking neural network. Finally

the neural network is trained and modeled by driving history data to achieve accurate prediction of arrival time. It is predicted that the optimization algorithm is compared with the unoptimized SNN algorithm and the Elman neural network algorithm by MATLAB simulation. The comparison results show that the CS-SNN prediction model has higher accuracy for the bus travel time prediction regardless of the working day or weekend

and the results are more stable.