Evolutionary regression prediction for software cumulative failure modeling: A comparative study

An evolutionary regression modeling approach for software cumulative failure prediction based on auto-regression order 4, 7 and 10 models are proposed. A real coded genetic algorithm is used to optimize the mean square of the error produced by training the auto-regression model. In this paper, we present a real coded genetic algorithm that uses the appropriate operators for this encoding type to train the auto-regression model. To evaluate the predictive capability of the developed model data sets, various projects were used. A comparison between auto-regression order 4 model trained using least square estimation and real coded genetic algorithm training is provided, also a comparison between the auto-regression order 7 and 10 models trained using the genetic algorithm is presented. Experimental results show that the training of different auto-regression model by the real coded genetic algorithm has a good predictive capability.