Selective laser melting (SLM) popularity is increasing day by day because of its ability to produce a satisfactory part quality. For getting the desired qualities of the product, the process parameters play a vital role in manufacturing. Therefore, the process parameters need to tune appropriately to get good products. Besides, researchers use quality predictive analysis with different combinations of the process parameters to improve the product quality in manufacturing. To predict product quality, the existing methods mostly focus on multiple inputs and one or two outputs-based prediction modeling, which is insufficient. Because more qualities of the products often test for qualifying a good product. That is why this thesis presents a multi-inputs and multi-outputs (MIMO) artificial neural network (ANN) model to predict the SLM product qualities. Among all process parameters used for SLM, four process parameters, that are laser power, scan speed, overlap rate, and hatch distance, have been chosen as the model inputs. And four of the important product’s quality measures, that are relative density, hardness, tensile strength, and porosity, are used as the model's outputs. In order to obtain an accurate neural network model, there are parameters such as the number of hidden layers and neurons in each hidden layer to optimize. This thesis uses the genetic algorithm (GA) to optimize the hidden layer and the number of neurons in each hidden layer from a given bound. After model optimization, sensitivity analysis is performed to evaluate the importance of the input parameters. Regarding the increased demand in SLM, it is also important to reduce its energy consumption. Therefore, an energy optimization method is developed using the neural network and genetic algorithm in this thesis. The objective of the optimization is to minimize the energy consumption of SLM manufacturing with a reduced compromisation of the quality requirements. The results presented in this thesis show a reduction in energy consumption of the selected SLM printer by 26% as compared to one existing study. The results of this study can be used in the industry to decrease their energy consumption further while maintaining the required quality.