This research investigates the machining of EN 31 alloy using a tungsten carbide tool coated with Al2O3+TiN+TiCN under different machining conditions. Surface roughness and power consumption during machining are analyzed, as these are critical parameters in the industry. The research is planned using the Taguchi l9 array, and optimization and prediction techniques are employed. The results are optimized using signal-to-noise ratio analysis, and two machine learning approaches, linear regression and artificial neural network, are utilized. The developed machine learning models predict the response with high accuracy, with the linear regression model achieving an accuracy of 95%, while the neural network model achieves an accuracy of 99.99%. The results of this research can provide insights into the use of coated tungsten carbide tools in machining EN 31 alloy under different machining conditions. Furthermore, the use of machine learning models can aid in the estimate and finding the best combination of machining limits, leading to improved surface quality and reduced consumption of electric power during machining. Overall, this research highlights the potential benefits of integrating machine learning techniques with traditional machining processes, opening up new avenues for research and development in the manufacturing industry.