ABSTRACT
Prioritization of development activities in software companies is
commonly performed arbitrarily and subjectively, based solely on
the experience of the company’s employees. Aiming to contribute
to the automation of this process, this paper presents a method
of automatic prioritization of software development activities, using
an algorithm that combines the use of a numerical regressionbased
Artificial Neural Network (RNA) with an ordering method.
To validate the accuracy of the proposed method, a case study was
conducted, with real data from a software development company.
The experiments allowed to evaluate the accuracy of the proposed
method qualitatively and quantitatively, generating satisfactory
results, which indicate the feasibility of implementing the proposed
method in the target company of the case study.