Quality tools help employees analyze and solve quality problems, providing measures required to detect a problem, determine its causes, plan and develop solutions, verify their effectiveness, and monitor their implementation. In manufacturing enterprises, they are also used in projects improving processes and products, mainly consisting in the effective use of resources possessed by an organization. The application of quality tools improves communication among managers, engineers and operators as well as helps in understanding processes and detecting possible causes of their variability. But only the correct selection of quality tools can bring benefits to an organization. The solution presented in the article [1] was the use of an artificial neural network-based model to automate the process of selecting appropriate tools. The present article describes the further stage of research related to supporting the selection of qualitative tools using neural networks. The continuation of the research consisted in expanding the set of quality tools with additional tools and training neural network models which support the selection of quality tools and comparing the effectiveness of neural networks using a smaller or greater number of tools. Ultimately, introducing such a model into an expert system can significantly simplify the work of less experienced employees, and thus contribute to faster and more effective problem-solving and organizational improvements.