Modern complex manufacturing processes require teams of researchers to properly model using tools like FEM, CFD and CALPHAD. Increases in computational power have enabled simpler machine learning techniques to reduce the overall cost of modelling while accomplishing the same result: a predictive tool. Laser Assisted Cold Spray (LACS) is a process with complex fields including fluid dynamics for particle acceleration in supersonic gas streams, high strain rate impacts, dynamic and static recrystallization, and heat transfer between particles and substrates. Instead of a physical model, the application of a machine learning algorithm to the critical inputs and outputs of the process can be used. These inputs have been determined to fall in three major categories: powder properties, substrate properties, and system parameters. The outputs include bond strength, porosity, hardness, and tensile strength. The validity, practicality, and predictive capabilities of both supervised and unsupervised machine learning algorithms for LACS will be discussed.