Laser-assisted cold spray (LACS) is a solid state supersonic powder deposition process wherein the powders are deposited onto a region of substrate heated by a laser. The process has high build rates, hard deposits, and is fairly cost-effective due to use of nitrogen as the carrier gas. All of these benefits are derived from a set of extremely complex impact phenomena including high strain, thermal gradients, material jetting, and supersonic gas exchange. As a result, predicting material properties based exclusively on a defined set of system parameters is extraordinarily difficult even for an experienced user. To combat this, research has begun focusing on a set of statistical algorithms that can handle complex, noisy, and limited data. Using data from input powders, substrates, and system parameters, these algorithms will be discussed regarding their ability to predict, with varying degrees of success, key resultant properties of LACS deposits.