Determining the strength of subgrade soil, crucial for flexible pavement design, traditionally relies on time-consuming and labour-intensive California Bearing Ratio (CBR) tests. The limitations of linear and non-linear regression-based prediction methods have led to an increased importance of soft computing techniques in providing flexible and consistent CBR predictions for practical engineering. This paper proposes a hybrid model that combines the Bayesian Optimization algorithm (BOA) with support vector regression (SVR) to predict CBR for subgrade soil in pavement design. A database of 238 soil test datasets from northern Algeria was utilised to develop the BOA-SVR model. Using the BOA technique to optimize hyperparameters can improve the model’s performance. The developed hybrid model closely matched experimental results, with a coefficient of determination of 89% and a mean squared error of 5.77, indicating high predictive accuracy. Comparative analysis shows that the BOA-SVR model performs better than conventional and other machine learning models in predicting CBR in tested subgrade soils, in terms of accuracy and robustness. Finally, the optimal subset of features from the initial dataset combined with the BOA-SVR model is determined using an exhaustive feature selection method that includes cross-validation. The results of the experiment indicate that the accuracy of the hybrid model that has been developed is improved by a subset of only seven features from the twelve initial features, this allows for the reduction of computing time and storage space.