Wire-feed laser additive manufacturing has gained attention for years with its promises of high-level automation, reducing materials waste, overall costs, and large-scale volume production. However, printing material with multiple desired bead properties is a great challenge due to the high cost of experimental data and trial and error methods and the interdependent correlations among the properties. This study proposes a comprehensive multi-property integrated design framework based on learning from experiments data to enable quality control of part (bead) surface finish, geometry and microstructural properties. The printed bead process – microstructure – geometry relationships and process features' importance scores are investigated. The overall bead quality (smooth, ripple, and failed), geometry (e.g. bead height, width, fusion zone depth, fusion zone area), and microstructures characteristics are simultaneously optimized to obtain the optimal processing window. Specifically, the desirable property thresholds are defined experimentally, and the microstructures and geometries of printed beads under various process combinations have been predicted by machine learning models and visualized in a 3D contour space. With these predictions, the process parameters are optimized by passing through a set of filters to filter out undesired process candidates from a process searching space. The validation results highlight that the process parameterizations optimized by this framework can speed up the manufacturing of materials with the desired bead multi-performance.