Regularized Fuzzy Neural Networks to Aid Effort Forecasting in the Construction and Software Development
This work addresses the challenge of effort forecasting for software engineering managers, but it appears incremental as it combines existing methods (neural networks and fuzzy systems) without claiming major breakthroughs.
The paper tackles the problem of predicting software development time by proposing a hybrid system combining artificial neural networks and fuzzy systems to create an interpretable expert system. The model was tested on a real database and showed promising results in aiding software construction predictability.
Predicting the time to build software is a very complex task for software engineering managers. There are complex factors that can directly interfere with the productivity of the development team. Factors directly related to the complexity of the system to be developed drastically change the time necessary for the completion of the works with the software factories. This work proposes the use of a hybrid system based on artificial neural networks and fuzzy systems to assist in the construction of an expert system based on rules to support in the prediction of hours destined to the development of software according to the complexity of the elements present in the same. The set of fuzzy rules obtained by the system helps the management and control of software development by providing a base of interpretable estimates based on fuzzy rules. The model was submitted to tests on a real database, and its results were promissory in the construction of an aid mechanism in the predictability of the software construction.