This research offers a comparative evaluation of machine learning models for the prediction of yield strength of 3D-printed metallic components based on manufacturing parameters. Focusing on the Ti-6Al-4V alloy manufactured using laser powder bed fusion (L-PBF), four regression models, multi-layer perceptron (MLP), support vector machine (SVM), linear regression, and decision tree were compared in terms of their predictive ability. The models were trained and cross-validated using a carefully chosen dataset from the scholarly literature. The performance was assessed using the mean square error (MSE), mean absolute error (MAE), and R-squared (R2) metrics. Among the models evaluated, the Decision Tree demonstrated the strongest predictive capability, effectively capturing complex dependencies within the dataset. It achieved the lowest error values and the highest coefficient of determination, with MAE = 36.17 MPa, MSE = 22,272.02 MPa2, and R2 = 0.808, underscoring its reliability. Laser power and scan speed consistently emerged as the most influential parameters. These findings highlight the value of machine learning–based predictive modelling as a tool for process optimisation and quality control in metal additive manufacturing. The contribution of this study lies in its systematic benchmarking of interpretable models on a reproducible dataset, although certain limitations remain—notably the reliance on secondary data and the exclusion of microstructural descriptors. Future research will incorporate additional parameters and explore ensemble and hybrid approaches for broader applicability.