In this study, predictive modelling was performed for the cutting forces generated during the orthogonal turning of AISI 316L stainless steel. An artificial neural network (ANN) and a multiple regression analysis were utilised. The input parameters of the ANN model were the cutting speed, feed rate and coating type. In the model, tungsten carbide cutting tools, uncoated and with two different coatings (TiCN + Al2O3 + TiN and Al2O3), were used. The ANN predictions closest to the experimental cutting forces were obtained for the main cutting force (F (c)) and the feed force (F (f)) by 3-7-1 and 3-6-1 network architectures with a single hidden layer, respectively. While the SCG learning algorithm provided the optimal results for F (c), the optimal results for F (f) were provided by the LM learning algorithm. A very good performance of the neural network, in terms of agreement with the experimental data, was achieved. With the developed model, the cutting forces could be precisely predicted depending on the cutting speed, feed rate and coating type. The prediction results showed that the ANN was superior to the multiple regression method in terms of prediction capability.