Materials designMaterials design has a significant impact on almost every modern industry, including the development of new energy materials, medical devices, high-performance electronic components, and sustainable environmentally friendly materials. The traditional methods of trial and error are often inefficient, time-consuming, and difficult to fully release the potential of materials. The integration of machine learningMachine learning (ML) has brought a paradigm shift in materials designMaterials design, which can quickly predict and optimize material properties. This chapter introduces the current machine learningMachine learning (ML) methods commonly used in materials design. We detailed traditional machine learning algorithmsMachine Learning Algorithms such as linear regression, decision treesDecision tree, support vector machinesSupport vector machine (SVM), neural networksNeural networks (NN), naive BayesK-Nearest Neighbor, k-nearest neighborsNearest neighbors, random forestsRandom forest (RF), and gradient boosting, and deep learningDeep learning (DL) models such as convolutional neural network, recurrent neural networks, long short-term memory network, generative adversarial network, autoencoder, graph neural networkNeural networks (NN), transformer model, capsule network, etc. These algorithms have shown great application ability in materials property predictionProperty Prediction, structure optimization, and new material discovery. Besides these, we provide a comparative analysis of deep learningDeep learning (DL) and traditional machine learningMachine learning (ML) methods and discuss their respective advantages, disadvantages, and applications in the field of material design. In the future, with the continuous progress of machine learningMachine learning (ML) technology and the strengthening of interdisciplinary cooperation, more breakthroughs are expected in material design and cheminformaticsCheminformatics.