The design of casting gating system directly determines the solidification sequence, defect severity, and overall quality of the casting. A novel machine learning strategy was developed to design the counter pressure casting gating system of a large thin-walled cabin casting. A high-quality dataset was established through orthogonal experiments combined with design criteria for the gating system. Spearman’s correlation analysis was used to select high-quality features. The gating system dimensions were predicted using a gated recurrent unit (GRU) recurrent neural network and an elastic network model. Using EasyCast and ProCAST casting software, a comparative analysis of the flow field, temperature field, and solidification field can be conducted to demonstrate the achievement of steady filling and top-down sequential solidification. Compared to the empirical formula method, this method eliminates trial-and-error iterations, reduces porosity, reduces casting defect volume from 11.23 cubic centimeters to 2.23 cubic centimeters, eliminates internal casting defects through the incorporation of an internally cooled iron, fulfilling the goal of intelligent gating system design.