Exploring the relationship between performance metrics and cost saving potential of defect prediction models

04/01/2021
by   Steffen Herbold, et al.
0

Performance metrics are a core component of the evaluation of any machine learning model and used to compare models and estimate their usefulness. Recent work started to question the validity of many performance metrics for this purpose in the context of software defect prediction. Within this study, we explore the relationship between performance metrics and the cost saving potential of defect prediction models. We study whether performance metrics are suitable proxies to evaluate the cost saving capabilities and derive a theory for the relationship between performance metrics and cost saving potential.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/11/2019

On the costs and profit of software defect prediction

Defect prediction can be a powerful tool to guide the use of quality ass...
06/05/2017

A Possibilistic and Probabilistic Approach to Precautionary Saving

This paper proposes two mixed models to study a consumer's optimal savin...
06/08/2021

Does class size matter? An in-depth assessment of the effect of class size in software defect prediction

In the past 20 years, defect prediction studies have generally acknowled...
04/26/2021

Revisiting the size effect in software fault prediction models

BACKGROUND: In object oriented (OO) software systems, class size has bee...
11/23/2021

Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation

Most set prediction models in deep learning use set-equivariant operatio...
01/12/2018

Benchmarking cross-project defect prediction approaches with costs metrics

Defect prediction can be a powerful tool to guide the use of quality ass...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.