The construction sector is a substantial generator of waste and carbon dioxide emissions worldwide. The use of sustainable materials in construction could minimize its negative effects on the environment. This research is intended to offer a soft computing model for predicting the deformation and parallel bending strength (PBS) of Guadua angustifolia applying an artificial neural network (ANN)-particle swarm optimization (PSO) approach and employing the data obtained from the experimental tests performed in the study. The input parameters (IP) utilized in the modeling process include the outside diameter, wall thickness, minimum length, external taper, perpendicular distance of bow, ISO ovality, eccentricity, actual shear span, area, modulus of elasticity, density, and linear mass. The resulting models showed R values of 0.99076 and 0.99976 and MAPE of 0.936% and 0.345% for deformation and PBS, respectively. The findings of the sensitivity analysis (SA) also exhibited that ISO ovality and eccentricity were the most important parameters to the deformation and PBS models. Research outcomes demonstrated the effectiveness of the ANN-PSO approach for predicting the deformation and parallel bending strength characteristics of Guadua angustifolia. The modeling approach proposed in this study could be utilized for speeding up the material characterization phase of similar construction materials.