Understanding the complex relationships between process, structure, and properties is crucial in materials science and engineering. This knowledge forms the foundation for innovation in the development of advanced materials. The ability to numerically predict a material's behavior during metal processing allows for the exploration of material properties beyond the limitations of traditional experiments. Achieving this requires the development of accurate material models that effectively describe how materials respond to various processing conditions. The current work is focused on the numerical simulation of metal forming operations and the derivation of constitutive laws. In the upcoming lecture, we will compare a physics-based approach to machine learning techniques. Specifically, we will investigate the symbolic regression method, which, unlike traditional "black-box" machine learning models, can produce interpretable results in the form of mathematical equations. This method not only automatically generates equations that predict material behavior under specific manufacturing conditions but also optimizes key performance metrics such as strength and elasticity. We will examine both compressive and tensile testing and predict the corresponding stress-strain curves for different types of metal alloys. Additionally, we will explore the potential for creating a hybrid model that combines data-driven and physics-based methodologies, paving the way for advancements in material design and optimization. By leveraging established material laws and equations, we can gain a deeper understanding of how materials respond to external forces.