In various industries, e.g., manufacturing, railways, and automotive, austempered ductile iron (ADI), is extensively used because of its desirable characteristics for example, high tensile strength with good ductility. The hardness and ductility of ADI can be tailor-made for a specific application by following an appropriate process. Such characteristics can be achieved by (i) adding a delicate proportion of several chemical compositions during the production of ductile cast iron and then followed by (ii) an isothermal heat treatment process, called austempering process. The chemical compositions, depending on the austempering temperature and its time duration, interact in a complex manner that influences the microstructure of ADI, and determines its hardness and ductility. Vickers hardness number (VHN) is commonly used as a measure of the hardness of a material. In this paper, we propose a computationally efficient enhanced multilayer perceptron (eMLP)-based technique to model the austempering process of ADI for prediction of VHN by taking experimental data reported in literature. By comparing the performance of the eMLP model with an MLP-based model, we have shown that the proposed model provides similar performance but with less computational complexity.