Laser cladding is a method of material deposition through which a powdered or wire feedstock material is melted and consolidated by use of a laser to coat part of a substrate. Determining the parameters to fabricate the desired clad bead geometry for various configurations is problematic as it involves a significant investment of raw materials and time resources, and is challenging to develop a predictive model. The goal of this research is to develop an experimental methodology that minimizes the amount of data to be collected, and to develop a predictive model that is accurate, adaptable, and expandable. To develop the predictive model of the clad bead geometry, an integrated five-step approach is presented. From the experimental data, an artificial neural network model is developed along with multiple regression equations. A multi-layer perceptron network application is employed which uses a feed forward back propagation network architecture for the overall training process through external data consisting of input (process parameters) and target (shape parameters) values. Once a desired level of network training is achieved, simulation results (predicted shape parameters) are generated for a new input data set within the trained network boundary conditions. Furthermore, a comparison between different approaches to sensitivity analysis (clamping technique and sensitivity index) is presented to illustrate the uncertainty in the outputs of the model in relation to its inputs. Experimental validation is conducted by predicting specific process parameters for unique bead geometry. The predicted and resulting bead geometry values are seen within the 95th percentile accuracy.