Objective A hybrid model based on bidirectional short term memory (BiLSTM) and Transformer was constructed to predict the population behavior of Listeria monocytogenes under different environmental conditions. Methods In view of the limitations of traditional machine learning methods in processing complex time series data, an innovative solution combining BiLSTM and Transformer model is proposed to effectively capture the long and short term dependence of time series and improve the prediction accuracy. The model input includes characteristics such as temperature, water activity, pH value, time and whether it is the initial bacterial concentration, etc. After data preprocessing, feature standardization and category coding, the trained model is used for prediction. The experimental data of Listeria monocytogenes from ComBase database were used to verify the model. Results The model performed well for several food groups, with R2 values of 0.72, 0.65, 0.85, 0.81 and 0.81 for beef, pork, medium, seafood and vegetables, and RMSE values of 1.17, 1.15, 0.89, 0.93 and 0.83, respectively. The results showed that the model could accurately capture the changing trend of bacterial population. By calculating the coefficient of deviation (Bf) and the coefficient of accuracy (Af), the advantages of the model both in forecasting accuracy and robustness are verified. Conclusion The BiLSTM-Transformer hybrid model provides an efficient and accurate method for predicting bacterial population behavior, which can provide a reference for bacterial prediction in the field of food safety.