›› 2012, Vol. 25 ›› Issue (6): 75-.

• Articles • Previous Articles     Next Articles

Software Defect Prediction Based on Cost-Sensitive Neural Networks

 MIAO Lin-Song   

  1. (College of Computer Science & Technology,Nanjing University of Aeronautics & Astronautics,Nanjing 210016,China)
  • Online:2012-06-15 Published:2012-08-23


Software defect prediction has been studied as an important research topic for 30 years in software engineering.Recently,with the development of machine learning techniques,traditional machine learning has been applied in software defect prediction based on static code attributes successfully.However,the traditional machine learning does not consider the cost-sensitive problem and class-imbalance problem in software defect prediction applications.We study the application of cost-sensitive neural networks based on over-sampling and threshold-moving to software defect prediction.The experimental results on NASA software defect prediction benchmarking dataset demonstrate the algorithm's efficacy.

Key words: software defect prediction;cost-sensitive neural networks;cost-sensitive;class-imbalance

CLC Number: 

  • TP391