Driven by the global carbon neutral policy, natural gas, especially shale gas, has gradually become an important part of the energy structure transformation due to its abundant reserves and low carbon emission characteristics. Intermittent production of shale gas is a strategy to restore formation pressure through periodic shut-in and opening-in operations. However, production forecasting is challenging due to the volatility and discontinuity of production data. Using production data from 17 typical intermittently producing shale gas wells in a gas field in Changning shale gas field, a unified feature set was constructed through feature extraction, and the GA-BP algorithm was applied to improve prediction accuracy. Through feature extraction, a unified feature set was constructed, and GA-BP algorithm was used to improve the prediction accuracy. The experimental results show that the model has high accuracy and stability in predicting the maximum pressure, maximum flow, average pressure and average daily output. This study provides scientific basis for optimizing production management and prolonging production life of shale gas wells.