Search

Classification algorithms that help to identify software defects or faults play a crucial role in software risk management. Experimental results have shown that ensemble of classifiers are often more accurate and robust to the effects of noisy data, and achieve lower average error rate than any of the constituent classifiers. However, inconsistencies exist in different studies and the performances of learning algorithms may vary using different performance measures and under different circumstances. Therefore, more research is needed to evaluate the performance of ensemble algorithms in software defect prediction. The goal of this paper is to assess the quality of ensemble methods in software defect prediction with the analytic hierarchy process (AHP), which is a multicriteria decision-making approach that prioritizes decision alternatives based on pairwise comparisons. Through the application of the AHP, this study compares experimentally the performance of several popular ensemble methods using 13 different performance metrics over 10 public-domain software defect datasets from the NASA Metrics Data Program (MDP) repository. The results indicate that ensemble methods can improve the classification results of software defect prediction in general and AdaBoost gives the best results. In addition, tree and rule based classifiers perform better in software defect prediction than other types of classifiers included in the experiment. In terms of single classifier, K-nearest-neighbor, C4.5, and Naïve Bayes tree ranked higher than other classifiers. [ABSTRACT FROM AUTHOR]

This paper considers the problem of numerically evaluating American option prices when the dynamics of the underlying are driven by both stochastic volatility following the square root process of Heston [18], and by a Poisson jump process of the type originally introduced by Merton [25]. We develop a method of lines algorithm to evaluate the price as well as the delta and gamma of the option, thereby extending the method developed by Meyer [26] for the case of jump-diffusion dynamics. The accuracy of the method is tested against two numerical methods that directly solve the integro-partial differential pricing equation. The first is an extension to the jump-diffusion situation of the componentwise splitting method of Ikonen and Toivanen [21]. The second method is a Crank-Nicolson scheme that is solved using projected successive over relaxation and which is taken as the benchmark for the price. The relative efficiency of these methods for computing the American call option price, delta, gamma and free boundary is analysed. If one seeks an algorithm that gives not only the price but also the delta and gamma to the same level of accuracy for a given computational effort then the method of lines seems to perform best amongst the methods considered. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]