Short-term passenger flow prediction strategy of urban rail transit based on ridge regression and LSTM

In order to reduce the interference of noise in the short-term passenger flow prediction of urban rail transit, an efficient and accurate traffic flow prediction scheme has become the most concerned issue for traffic participants. This paper focuses on the application of ridge regression and LSTM neural network in the short-term passenger flow of urban rail transit. This paper firstly performs data cleaning, missing processing and normalization. Then, we choose LSTM as the core and use the ridge regression-assisted model to predict the short-term passenger flow of urban rail transit. Ridge regression is used for prediction when there is less data, and LSTM with high fitting degree is used for medium and long-term prediction. The model has a high fitting effect on the randomly divided test set and real data.