Investigation of the geotechnical characteristics of eighteen different lateritic soils within southwest Nigeria was carried out to determine their suitability for road construction. To achieve this goal, the lateritic soils samples were subjected to different laboratory tests, including specific gravity, Atterberg limits, grain size analysis, California bearing ratio, and compaction, in accordance with the ASTM standard procedure. The results of the tests showed that the specific gravity varied between 2.55 and 2.81; the linear shrinkage varied between 6.68% and 10.98%; the liquid limit varied between 37.17% and 56.93%; the plastic limit ranged from 19.47% to 37.14%; the plasticity index ranged from 3.81% to 30.29%; the fine sand content ranged from 37.07% to 62..93%; the fines content ranged from 36.4% to 60.9%; the maximum dry density ranged from 1747 kg/m3 to 2056 kg/m3 ; the optimum moisture content ranges from 10.94% to 20.51%; the un-soaked California bearing ratio ranged from 14.7% to 45.6%; and the soaked California bearing ratio ranged from 10% to 31%. Based on these results, all the studied soils can be used as road subgrade, while none except Loc.5/S1 is suitable for road subbase. However, none of the soils meets up with the requirement for road base course. The suitability of laterite for the construction of road depends largely on the California bearing ratio. However, laboratory tests for determining the California bearing ratio is tedious, time consuming and costly. As a result of this difficulty, there is a need to develop soft computing models to predict laterite California bearing ratio from index properties with cheap and simple tests. Thus, the experimental datasets of the eighteen studied lateritic soils were used to create and train artificial neural network (ANN) models to predict California bearing ratio from liquid limits, plasticity index, linear shrinkage, fine sand content and fines content. The proposed ANN models were compared with the multiple linear regression models proposed in this study and various regression based models suggested in the literature via statistical analyses. Based on the model comparison, the proposed ANN models outperformed the rest of the models; they presented the highest R 2 and the lowest RMSE, MAPE and MAE values. Thus, the ANN models are validated. To enhance the practical application of the proposed ANN models, they were transformed into simple mathematical equations, which gave the same predictions as the direct ANN models. Thus, they can be used for practical purposes.