Machine learning prediction models for thin wire-based metal additive manufacturing(MAM) process are proposed, aiming at the complex relationship of the process parameters and the geometric characteristics of single track of the deposition layer and surface roughness. The basic effects of laser power, wire feeding speed, and scanning speed on the width and height of the single track and surface roughness are experimentally studied, and the results show that laser power has a significant impact on the width of the single track, but has little effect on the height. As the wire feeding speed increases, the width and height of the single track increase, especially for the height. The faster the scanning speed, the smaller the width of the single track, while the height does not change much. Then, support vector regression (SVR) and artificial neural network regression (ANN) methods are employed to set up prediction models. The SVR and ANN regression models perform well in predicting the width, with a smaller RMSE and a higher correlation coefficient R2. Compared to the ANN model, the SVR model performs better both in predicting geometric characteristics of single track and surface roughness. Multi-layer thin-walled parts are manufactured to verify the accuracy of the models.