The manuscript presents a hybrid machine learning approach for predicting the unconfined compressive strength (UCS) of cement-stabilized lateritic soil, which demonstrates a certain degree of innovation by combining SAO and DAOA with a Naïve Bayes model. The integration of advanced optimization techniques into geotechnical modeling is commendable and relevant for sustainable infrastructure development. However, the manuscript lacks sufficient detail regarding the dataset used. The number of samples, data distribution, and preprocessing steps are not clearly described, making it difficult to assess the robustness and representativeness of the training and testing processes. Additionally, the generalization capability of the proposed model is not discussed, especially with regard to its applicability to other soil types or varying environmental conditions. These omissions raise concerns about the reliability and transferability of the proposed methodology.