ABSTRACT The flow stress prediction of the 92W-5Co-3Ni alloy is performed using Machine Learning models like Artificial Neural Networks (ANN), Random Forest (RF) and Deep Neural Networks (DNN). Initially, the compression tests were done on the Gleeble-3800 Thermo-Mechanical Simulator at strain rates (1s−1, 25s−1,50s−1, 75s−1,100s−1) and temperature (room temperature (RT), 200°C, 400°C, 600°C). It was seen that flow stress is highly sensitive to temperature rather than strain rates. The true stress-strain curves showed a declining trend at room temperature, but true stress stabilises at higher temperatures. On comparison of experimental flow stress with the predicted flow stress of all models, the RF model had predicted best with a high correlation coefficient of 0.9979 and least error of 0.38%. The DNN model predicted second better with a 0.9964 correlation coefficient but with the highest absolute error of 0.83% compared to the other two models. Among all these models, the ANN model demonstrates the least correlation coefficient of 0.9927 than other models.