Software Process Improvement provides benefits to organizations, however, efforts to improve aren't guided by the combined use of Critical Success Factors and Good Practices to be applied, dedicating resources without a prior analysis to guide the actions intentionally. The research proposes an intelligent system for decision making support in Software Process Improvement, taking as reference the Critical Success Factors and Good Practices that an organization can apply to improve its state. In order to achieve this, an intelligent system is conceived, which, based on Artificial Intelligence techniques, optimizes improvement scenarios through the implementation of a genetic algorithm and the application of rules of association between good practices and critical success factors, predicts the success of scenarios improvement through an evolutionary artificial neural network and offers recommendations to achieve them. The methods used to validate the results corroborated the contribution and usefulness of the proposal.