An Artificial Neural Network Approach to Software Testing Effort Estimation

Trying to predict the effort needed to test prewritten software is a complex problem as the amount of work involved in software testing depends on a number of independent and related factors (for example, lines of code, unit complexity etc.). Artificial neural networks appear well suited to problems of this nature as they can be trained to understand the explicit and inexplicit factors that drive a testÕs cost. For this reason, artificial neural networks were investigated as a potential tool to improve software testing effort estimation using project data supplied by Rolls-Royce and Associates Limited. In addition, in order to deal with uncertainties that exist in modelled results, statistical analyses were employed to identify confidence intervals for predicted costs. This paper discusses these analyses and comments on the results that were obtained when artificial neural networks were developed, trained and tested on the data