DeepAI AI Chat
Log In Sign Up

The Impact of Feature Selection on Predicting the Number of Bugs

by   Haidar Osman, et al.
Universität Bern

Bug prediction is the process of training a machine learning model on software metrics and fault information to predict bugs in software entities. While feature selection is an important step in building a robust prediction model, there is insufficient evidence about its impact on predicting the number of bugs in software systems. We study the impact of both correlation-based feature selection (CFS) filter methods and wrapper feature selection methods on five widely-used prediction models and demonstrate how these models perform with or without feature selection to predict the number of bugs in five different open source Java software systems. Our results show that wrappers outperform the CFS filter; they improve prediction accuracy by up to 33 eliminating more than half of the features. We also observe that though the same feature selection method chooses different feature subsets in different projects, this subset always contains a mix of source code and change metrics.


page 6

page 9


Revisiting reopened bugs in open source software systems

Reopened bugs can degrade the overall quality of a software system since...

Predicting Crash Fault Residence via Simplified Deep Forest Based on A Reduced Feature Set

The software inevitably encounters the crash, which will take developers...

Predicting the Number of Reported Bugs in a Software Repository

The bug growth pattern prediction is a complicated, unrelieved task, whi...

AutoSpearman: Automatically Mitigating Correlated Metrics for Interpreting Defect Models

The interpretation of defect models heavily relies on software metrics t...

Powershap: A Power-full Shapley Feature Selection Method

Feature selection is a crucial step in developing robust and powerful ma...

Outlier Detection as Instance Selection Method for Feature Selection in Time Series Classification

In order to allow machine learning algorithms to extract knowledge from ...