This research employs a data-driven approach to optimize the plasma arc cutting process. The evaluation of cut quality is based on six output characteristics, while the input parameters include stand-off distance, cutting current, and cutting speed. The output metrics consist of the material removal rate (MRR), surface roughness, bevel angle, slag formation, kerf width, and heat-affected zone (HAZ). Given the complexity of the process and the multitude of involved processing parameters, it is imperative to develop an optimization model to ensure the production of undisturbed structures. The primary aim of this study is to identify the most critical factors that facilitate optimal conditions for plasma arc cutting. The research goal is to determine the influence of input parameters on the plasma arc cutting quality using an adaptive neural fuzzy inference system (ANFIS). It has been found that the material removal rate (MRR), surface roughness, bevel angle, slag formation, kerf width, and heat-affected zone (HAZ) are predominantly affected by the interplay of cutting current and stand-off distance. Ideally, the best predictive model for various attributes, such as MRR, bevel angle, slag formation, surface roughness, kerf width, and HAZ, is one that synergistically combines cutting current and stand-off distance. This study, which evaluates multiple input parameters simultaneously, is expected to attract significant attention as it represents a pioneering small-scale investigation in the field.