Hydraulic fracturing is a crucial method in shale oil development, and predicting production after hydraulic fracturing is one of the challenges in shale oil development. Conventional methods for predicting production include analytical methods and numerical simulation methods, but these methods involve many parameters, have high uncertainty, and are time-consuming and costly. With the development of shale oil development, there are more and more sample data on the geological parameters, engineering parameters, and development parameters of shale oil hydraulic fracturing, making it possible to use machine learning methods to predict production after hydraulic fracturing. This article first analyzes the impact of different parameters on initial production and recoverable reserves based on field data from Chang-7 shale oil in the Ordos Basin of China. Then, using the Particle Swarm Optimization (PSO) algorithm and the Gradient Boosting Decision Tree (GBDT) algorithm, machine learning models for initial production and recoverable reserves are established. The Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive exPlanations (SHAP) explanation methods are used to explain the models. The study found that initial production is highly correlated with parameters such as the number of fracturing stages and fracturing fluid volume, while recoverable reserves are significantly related to parameters such as well spacing, area, and reserver-controlled. The PSO-GBDT model established in this study has an accuracy of over 85% and can be used for production prediction and subsequent parameter optimization research. By comparing the LIME and SHAP local explanation methods, it is shown that different explanation methods can obtain reasonable and credible local explanation results. This article establishes a high-precision shale oil well production prediction model and two model interpretation methods, which could provide technical support for shale oil well production prediction and production analysis.