For shale gas reservoir, fracture network fracturing in horizontal well is the key technology to guarantee its commercial exploitation, and the load recovery is a critical parameter which determines the post-fracturing performance. It has been reported that there is a huge difference in load recovery but the control factors are not well understood. It seriously affects the stimulation effect of fracture network fracturing in shale gas wells. Therefore, it is important to analyze the main control factors affecting the load recovery to optimize the design of fracture network fracturing. Further, the load recovery is affected by many factors such as geological, engineering, and production. However, traditional methods are blind to the accurate analysis of the impact on the load recovery. Notably, machine learning (ML) technology has achieved remarkable success in solving the problems of multi-factor nonlinear fitting and black box prediction. Therefore, the genetic expression programming (GEP) is adopted to express the nonlinear relationship in a clear and precise manner in this paper. The data of 189 wells were collected in southern Sichuan, including geological and engineering factors. A feature comprehensive index calculation method was established, and the relative importance of these features analyzed, and then screened out 18 reconstructed features based on geological and engineering factors that affect flow back. The mutual influence between the features was eliminated through principal component analysis of the reconstructed features. Thus the load recovery calculation model was developed and the influence of main control features (variables) on the flow back was analyzed by using partial dependence plot. Statistical parameters showed that satisfactory performance can be obtained through GEP model (training set R = 0.835, test set R = 0.815). The research results show that the GEP calculation model can quickly and accurately calculate the load recovery, obtain the influence law of main controlling factors of geological engineering on shale gas flow back and improve the control of load recovery. Therefore, the method based on GEP can effectively study the main control factors affecting the flow back of shale gas, and hence it can be used as a fast reliable tool to effectively evaluate the load recovery.