Name
Abstract | ||
|---|---|---|
The prediction of software defect-fixing effort is important for strategic resource allocation and software quality management. Machine learning techniques have become very popular in addressing this problem and many related prediction models have been proposed. However, almost every model today faces a challenging issue of demonstrating satisfactory prediction accuracy and meaningful prediction results. In this paper, we investigate what makes high-precision prediction of defect-fixing effort so hard from the perspective of the characteristics of defect dataset. We develop a method using a metric to quantitatively analyze the unpredictability of a defect dataset and carry out case studies on two defect datasets. The results show that data unpredictability is a key factor for unsatisfactory prediction accuracy and our approach can explain why high-precision prediction for some defect datasets is hard to achieve inherently. We also provide some suggestions on how to collect highly predictable defect data. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/QSIC.2010.40 | QSIC |
Keywords | Field | DocType |
defect dataset characteristics,software quality,satisfactory prediction accuracy,learning (artificial intelligence),related prediction model,mae,software defect fixing effort prediction,defect-fixing effort,resource allocation,meaningful prediction result,strategic resource allocation,program debugging,machine learning technique,defect datasets,unsatisfactory prediction accuracy,predictable defect data,defect dataset,high-precision prediction,data unpredictability,machine learning,software defect-fixing effort prediction,software quality management,predictive models,learning artificial intelligence,support vector machines,accuracy,prediction algorithms,data models,prediction model | Data modeling,Data mining,Computer science,Software bug,Support vector machine,Software quality management,Software,Resource allocation,Artificial intelligence,Software quality,Machine learning,Quality management | Conference |
ISSN | ISBN | Citations |
1550-6002 E-ISBN : 978-0-7695-4131-0 | 978-0-7695-4131-0 | 0 |
PageRank | References | Authors |
0.34 | 15 | 5 |