Surface texture plays an important role in reducing friction, which has been widely applied in mechanical equipment. In this paper, a surface texture design method for sliding friction pairs based on machine learning is proposed, which consists of three parts: model training and construction, texture design and result verification. Firstly, artificial neural network (ANN) and gradient boosting decision tree (GBDT) are selected as the optimal forward and reverse models respectively by comparing five machine learning models. Then the optimal forward and reverse models are combined to design surface texture and verify the design results. The results show that the combination of forward and reverse models is reliable. Lubricant viscosity and friction coefficient obviously affect the design of texture size, depth and coverage. Finally, the feasibility and effectiveness of this method are validated by friction experiments. The results provide a new approach for the design of surface texture.