To investigate the effects of load distribution parameters of the diffuser vanes on the efficiency and pressure pulsation of the volute centrifugal pump, the diffuser shape was designed using an inverse design method, and an optimization method was proposed for the diffuser blade load distribution based on the combination of Latin hypercubic sampling, artificial neural network, and non-dominated sorting genetic algorithm-II. Steady and unsteady simulations were performed by solving the three-dimensional Reynolds-averaged Navier–Stokes equations using the shear stress transport k−ω turbulence model. The results obtained from Pearson correlation analysis revealed that the slope values Ks and Kh of the shroud and hub load distribution curves had the most significant effect on the pump head and efficiency. Compared with those of the original model, the efficiency and head of the optimized volute centrifugal pump under the design conditions increased by 3.8 and 3.5 %, respectively. The pressure pulsation intensities in the vaneless regions were effectively mitigated for the optimized volute centrifugal pump. The pressure pulsation coefficients at three times the diffuser vane frequency (3fDIF) reduced by 58.5 and 43.8 % at monitoring points M1 and M2, in the impeller outlet, respectively. The pressure pulsation coefficients at the impeller blade passing frequency (fBPF) reduced by 6.5 and 14.4 % at monitoring points M3 and M4 in the diffuser inlet, respectively. The results showed that the optimized diffuser improved the overall performance of the volute centrifugal pump, and demonstrated the feasibility of the optimization method.