Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Multi-stage Dynamic Selection for Cross-Project Defect Prediction

Source

arXiv

arxiv.org/abs/2607.20151v1

Read the source

Source

Plain-Language Brief

The paper proposes a new framework for Cross-Project Defect Prediction (CPDP) that addresses distribution shift issues between training and target projects by using a two-stage multiple classifier system selection scheme. The first stage evaluates various MCS configurations to find one that performs well across multiple training projects, resulting in a diverse set of specialized classifiers. The second stage selects the most competent classifiers for each new module in the target project at test time, making the system more robust to changes in distributions between training and target projects. The proposed approach outperforms existing CPDP methods in most scenarios as demonstrated by experimental results using 82 projects from four different benchmark datasets.

What the Document Says

  • The paper introduces a new framework for Cross-Project Defect Prediction (CPDP).
  • The framework uses a two-stage multiple classifier system (MCS) selection scheme.
  • The first stage evaluates MCS configurations to find one that generalizes well across multiple training projects, resulting in diverse classifiers.
  • The second stage selects the most competent classifiers for each new module in the target project at test time.
  • The proposed approach outperforms existing CPDP methods in most scenarios according to experimental results.
  • The experiments use 82 projects from four different benchmark datasets.

Key Concepts Mentioned

  • Cross-Project Defect Prediction (CPDP)
  • Multiple Classifier System (MCS)
  • Distribution shift
  • Software modules

Claims Made by the Document

  • The proposed approach outperforms existing CPDP methods in most scenarios.

Evidence Used

  • Experimental results using 82 projects from four different benchmark datasets demonstrate that the proposed approach outperforms the state-of-the-art CPDP methods.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Cross-Project Defect Prediction (CPDP) involves building models using data from external projects, called training projects, to predict modules from the target project. However, traditional CPDP methods suffer from the distribution shift between training and target projects that affects the model's performance. This paper proposes a novel CPDP framework that addresses this issue by proposing a two-stage multiple classifier system (MCS) selection scheme: one working at the project level and another at the module level. In the first stage, the framework evaluates multiple possible MCS configurations to find one that covers and generalizes well across multiple training projects. Consequently, the proposal is likely to obtain a diverse set of classifiers, each specialized in tackling software modules with distinct characteristics. The second selection stage operates at test time, selecting the most competent classifiers to predict each new module in the target project. Unlike previous approaches that apply the same classifiers to the entire target project, the proposed framework performs module-level model selection. This way, the system is more robust to changes in distributions between training and target projects because the selected set of classifiers is module-dependent. Our experimental results using 82 projects from four different CPDP benchmark datasets demonstrate that the proposed approach outperforms the state-of-the-art CPDP methods in most scenarios. The code, dataset, and further details about the proposed method are publicly available at https://github.com/jsaj/Multi_DES.