Resumen de A radial basis function neural network for predicting the effort of software projects individually developed in laboratory learning environments
Cuauhtémoc López-Martín, Ivica Kalichanin-Balich, Rosa Leonor Ulloa-Cazarez, Noel García-Díaz
Prediction techniques have been applied for predicting dependent variables related to Higher Education students such asdropout, grades, course selection, and satisfaction. In this research, we propose a prediction technique for predicting theeffort of software projects individually developed by graduate students. In accordance with the complexity of a softwareproject, it can be developed among teams, by a team or even at individual level. The teaching and training aboutdevelopment effort prediction of software projects represents a concern in environments related to academy and industrybecause underprediction causes cost overruns, whereas overprediction often involves missed financial opportunities.Effort prediction techniques of individually developed projects have mainly been based on expert judgment or based onmathematical models. This research proposes the application of a mathematical model termed Radial Basis functionNeural Network (RBFNN). The hypothesis to be tested is the following: effort prediction accuracy of a RBFNN isstatistically better than that obtained from a Multiple Linear Regression (MLR). The projects were developed by followinga disciplined development process in controlled environments. The RBFNN and MLR were trained from a data set of 328projects developed by 82 students between the years 2005 and 2010, then, the models were tested using a data set of 116projects developed by 29 students between the years 2011 and first semester of 2012. Results suggest that a RBFNN havingas independent variables new and changed code, reused code and programming language experience of students can beused at the 95.0% confidence level for predicting the development effort of individual projects when they have beendeveloped based upon a disciplined process in academic environments.
