 This paper proposes a new methodology for estimating the undrained shear strength of clay. It combines the CADBoost algorithm with Bayesian optimization to identify the most influential soil parameters in determining the strength of clay. This methodology is then applied to a set of experimental data collected from Finnish clay. The results show that the proposed methodology can accurately estimate the undrained shear strength of clay. Furthermore, the parameter uncertainty can also be taken into account when calculating the strength of clay. This article was authored by Hua Jinyang, Shikue Lu, Yuan Tao Li, and others.