TestBrain Risk Model
TestBrain’s machine learning analyzes your commit history to determine the risk of defect in each code change.
Analyzes Historical Commit and Defect Data
To build a model of the factors contributing to code defects, TestBrain’s machine learning reviews the code development history using:
- The git blame feature of git-based repositories to find bugs and bug fixes applied over the entire development history.
- Optional integration with Jira or other defect management tool to import a database of defects and the commits that caused them.
- On-going learning once TestBrain is installed from visibility into new test failures.
Machine Learning Builds a Defect Risk Model
TestBrain looks for patterns in the commits which led to defects in the past and uses these patterns to determine the probability of defects in new commits. A few of the factors the model considers include:
- commit details: size of commit, number of files changed, number of files and areas affected
- area of code changed: some areas of the code area more defect prone than others, or may be stale code
- purpose of commit: whether the commit is adding new code, updating legacy code, or fixing a bug
- developer habits: whether the code was submitted at unusual times or before a deadline; how much experience the developer has with this area of the code
- other activity: how many other developers are working on the same code area
Want More Technical Details?
Read the TestBrain machine learning white paper that explains the TestBrain risk model in detail.