Modern technology demands the development of strong and flame-resistant multifunctional thermoplastic-based nanocomposites that are also compatible with three-dimensional (3D) printing, as this method has become a standard production process in essential industries. This study tackles the two challenging steps in creating such multifunctional based materials: sample preparation (3D printing in this case), and material design. Accordingly, one of the primary objectives of this study is to develop a machine learning model for forecasting the printing and resultant properties of PNCs while encompasing both material properties and printing parameters. In this first year, efforts have been made to validate the hypothesis and identify appropriate material indicators for prediction through thermal and rheological experiments. The other key objective of the study is to develop strong and flame-retardant PNCs using a completely automated, data-driven approach that combines the synergistic effects of nanomaterials and flame retardant additives. The study aims to do multi objective composition optimization through data-driven methods, specifically Latin hypercube sampling (LHS) and Bayesian optimization (BO). The latter part of the initial year was dedicated to validating the experimental setup and optimization method, using a simple system based on PLA, NC, GNP, and boron nitride (BN).