Semester

Fall

Date of Graduation

2010

Document Type

Thesis

Degree Type

MS

College

Statler College of Engineering and Mineral Resources

Department

Lane Department of Computer Science and Electrical Engineering

Committee Chair

Bojan Cukic.

Abstract

In practical software development projects, solving test issues efficiently during Software Development Life Cycle is critical to release software products on time. Different test environments, test resources and test requirements could result in different outcomes. Therefore, getting accurate prediction of the software defects' resolution time could be beneficial to the practical projects.;In our study, data mining techniques offer great promise in prediction of software defects' resolution time. Our research is conducted based on the NASA Metrics Data Program (MDP). We first calculate the resolution time for available projects. Using unsupervised discretization methods, we split resolution time into certain interval as response variable. Then, investigating the relationship between metric properties and time intervals, we fit a model that attempts to produce prediction on resolution time. Experiments and analysis successfully demonstrate the feasibility of our approach.

Share

COinS