Resumo. The succinic acid is a microorganism common metabolite used in the food market which is produced exclusively by fermentation, and great attention has been given to the use of renewable raw materials for this purpose. This study aimed to determine the variables that influence the production of succinic acid by fermentation using Actinobacillussuccinogenes strain (CIP 106512) through a fractional factorial design and to test different architectures of artificialneural networks to model this process. Artificial neural networks are madeof three layers and were the MultilayerPerceptron (MLP) type, with Backpropagation learning algorithm. Experimental data for learning and testing ofnetworks were used, 13 and 6, respectively. The number of neurons in the hidden layer, learning rate and activationfunctions was varied. After evaluation of architectures, it was found that the sigmoidal activation function showed abetter performance than the hyperbolic tangent and that the number of neurons and learning rate directly influencethe error. The neural model with the lowest squared error was the network with the sigmoid function, learning rate0,1 and 5 neurons in the intermediate layer. This work allowed to determine which variables most influence in thesuccinic acid production and in the construction of the neural model for this process.