The art and science of structural engineering have played a vital role in shaping the built environment, often relying on methodologies that are far from optimal. Parametric design has become a widely used method among structural engineers for design exploration and better collaboration with architects in the early design stages. Combined with the increasing integration of Artificial Intelligence into everyday applications, this approach others the potential to enhance the current methodologies and make the use of finite element software more accesible.In this thesis, a parametric finite element model has been developed to generate a wide range of structural topologies to train a machine learning regression model capable of predicting material quantities in terms of embodied carbon. The parameterized algorithm focuses on frame-core wall structural systems of arbitrary 2D shapes, though the model is trained with a limited set of shape variations.The main algorithm enables rapid finite element model creation based on simple geometric inputs and allows for the identification of potential material optimization. Despite some simplifications, such as simplified wall distribution and uniform core cross-sections, the analytical approach taken achieves reasonable accuracy and provides significant value in the design exploration in early stages. Meanwhile, the prediction results demonstrate the potential of using machine learning to estimate embodied carbon despite inconsistencies in the results, highlighting the quasi-linear nature of the problem due to the aforementioned simplifications and the potential for data-driven insights.The study successfully provides a foundation for further exploration of embodied carbon prediction using artificial intelligence, offering a pathway toward more efficient design practices.