Neuro-genetic prediction of software development effort

Abstract

Prediction of resource requirements of a software project is crucial for the timely delivery of quality-assured software within a reasonable timeframe. Many conventional (model-based) and AI-oriented (model-free) resource estimators have been proposed in the recent past. This paper presents a novel genetically trained neural network (NN) predictor trained on historical data. We demonstrate substantial improvement in prediction accuracy by the neuro-genetic approach as compared to both a regression-tree-based conventional approach, as well as backpropagation-trained NN approach reported recently. The superiority of this new predictor is established using n-fold cross validation and Student's t-test on various partitions of merged Cocomo and Kemerer data sets incorporating data from 78 real-life software projects.