High-temperature superconducting (HTS) pancake coils play an essential role in numerous applications such as HTS transformers, Superconducting Magnetic Energy Storage (SMES) systems, and high-field magnets, among others. Recently, AI-powered cyber-physical systems (CPS) have made significant progress and are expected to enable rapid design, accelerated design optimization, and enhanced efficiency in HTS systems. This study employs the 2D axisymmetric T-A homogenization method to investigate the influence of geometrical and operational parameters on AC transport losses. A total of 2,700 Finite Element Method (FEM) simulations were generated. However, for readability and conciseness, only a specific fraction of these simulations, 270 cases, were analyzed in detail so that each parameter varied individually while keeping others constant. Regression analysis has been also performed to capture the relationship between AC transport losses versus geometrical and operational parameters. The results reveal distinct nonlinear dependencies. The turn number follows a nonlinear trend similar to the E-J power law, for which a fitting curve formula was derived. Inner radius and applied current amplitude also exhibit nonlinear behavior, though without a clear fitting curve due to interdependencies with other parameters. The effect of HTS tape width was also qualitatively analyzed for both 10 mm and 12 mm cases, while the influence of critical current was examined for \({\text{I}}_{{\text{c}}} =\) 300 A, and \({\text{I}}_{{\text{c}}} =\) 400 A, highlighting its impact on AC transport losses. This study establishes detailed correlations between AC transport losses and key parameters, offering valuable insights for optimizing HTS coil design. The findings provide a basis for AI-driven predictive modeling and optimization, contributing to the development of the next-generation of HTS devices within CPS frameworks.