Objective To predict the stress on the anterior cruciate ligament (ACL) in the left leg of a volleyball player during ball-snapping landing, using an XCM deep neural network model. Methods A complete finite element model of the knee joint was established based on magnetic resonance (MR) and CT images. The kinematic and kinetic data of the volleyball player were collected synchronously using an eight-lens Qualisys motion capture system and a Kistler three-dimensional (3D) force platform. The knee joint moments were calculated using the musculoskeletal model in OpenSim. The joint moments were used as the input to the finite element model, with ACL stresses as the output. The kinematic and kinetic data were used as the input for the neural network, with ACL stress as the output. Results The peak equivalent ACL stress of the volleyball player during ball-snapping landing was (27.7±0.36) MPa, the maximum principal stress was (8.2±0.23) MPa, the maximum shear stress was (14.7±0.32) MPa, the equivalent strain was (5.7±0.008)%, the maximum principal strain was (5.0±0.006)%, and the maximum shear strain was (7.6±0.009)%. The normalized root mean square error (NRMSE) between the predicted and calculated values ranged from 5.84% to 7.12%. The root mean square error (RMSE) ranged from 0.251 to 0.282. Conclusions The XCM model can predict the ACL stress during volleyball spikes within a certain range. This study has provided a new method to obtain biomechanical data on volleyball players as well as an effective method to help volleyball players prevent ACL injuries.