In this paper, a tree based neural network viz. MARS (Friedman, 1991) for the modelling of the yield strength of a steel rolling plate mill is described. The inputs to the time series model are temperature, strain, strain rate, and interpass time and the output is the corresponding yield stress. It is found that the MARS-based model reveals which variable's functional dependence is nonlinear, and significant. The results are compared with those obta.ined by using a Kalman filter based online tuning method and other classification methods, e.g. CART, C4 .5, Bayesian classification. It is found that the MARS-based method consistently outperforms the other methods.