Comparison of software-reliability-growth predictions: neural networks vs parametric-recalibration
Renate Sitte · IEEE Transactions on Reliability · 1999
This paper compares empirically the predictive performance of two different methods of software reliability prediction: 'neural networks' and 'recalibration for parametric models'. Both methods were claimed to predict as good or better than the conventional parametric models that have been used-with limited results so far. Each method applied its own predictability measure, impeding a direct comparison. To be able to compare, this study uses a common predictability measure and common data-sets. This study reveals that neural networks are not only much simpler to use than the recalibration method, but that they are equal or better trend (variable term) predictors. The neural network prediction is further improved by preparing the data with a running average, instead of the traditionally used averages of grouped data points. Neural network predictions do not depend on prior known models. Off-the-shelf neural network software tools make it easy to apply the method.