An empirical model is developed to predict the mechanical properties that steel inherits from the hot-rolling process and its chemical composition. In this process, slabs of steel are heated and rolled into thinner sheets which are either coiled or cut into plates. The mechanical properties of the coils and plates are sampled and must conform to national and international standards for steel products. The aim here is to use the statistical technique of multiple linear regression to develop relationships between the mechanical properties and the various processing temperatures and concentrations of chemical elements present in the steel. This analytical tool will allow better understanding of the steel making process and the ability to vary input parameters to improve the product. In particular the number of coils and plates which fail mechanical testing may be able to be reduced, with a subsequent fall in production costs.