Skip to main navigation Skip to search Skip to main content

PROPER-SDP: PROmpt-Based Project Evolution-awaRe Software Defect Prediction for Edge-Cloud Systems

  • Inseok Yeo
  • , Sungu Lee
  • , Duksan Ryu
  • , Jongmoon Baik*
  • *Corresponding author for this work
  • Korea Advanced Institute of Science and Technology

Research output: Contribution to conferenceConference paperpeer-review

Abstract

Edge-cloud systems, which bring computing, storage, and networking resources closer to end-users, offer significant advantages in reducing latency and enabling real-time data processing. Ensuring software reliability in these environments is critical, which has led to growing attention on Just-in-Time (JIT) defect prediction as an effective technique for prioritizing testing efforts by identifying code changes likely to introduce defects. However, edge-cloud systems often face challenges such as data scarcity, rapid project evolution, and limited historical defect information. These characteristics lead to the cold-start problem, where prediction models struggle to perform accurately on new or low-data projects due to the lack of training data. In this paper, we propose a novel prompt-based approach that uses Large Language Models (LLMs) in a prompt-based framework. By incorporating project evolution data directly into prompts, our approach enables LLMs to effectively capture the contextual information essential for accurate JIT defect prediction. Evaluation results demonstrate that our method significantly improves prediction performance, surpassing baseline method by an average of 13% in F1 score. This approach offers a practical solution for achieving high-accuracy JIT defect prediction in resource-constrained, rapidly evolving edge-cloud environments.

Original languageEnglish
Title of host publicationThe Inclusive Web
Subtitle of host publicationRealizing Safe, Accessible, Inclusive, and Sustainable Web Engineering - 25th ICWE 2025 International Workshops, BECS, SWEET, 2025, Revised Selected Papers
EditorsYen-Chia Hsu, Kari Systä, In-Young Ko, Filippo Gramegna
PublisherSpringer Science and Business Media Deutschland GmbH
Pages68-81
Number of pages14
ISBN (Print)9783032112323
DOIs
StatePublished - 2026
Event5th International Workshop on Big Data Driven Edge Cloud Services, BECS 2025 and 3rd International Workshop on the Semantic WEb of EveryThing, SWEET 2025, co-located with 25th International Conference on Web Engineering, ICWE 2025 - Delft, Netherlands
Duration: 2025.06.302025.07.3

Publication series

NameCommunications in Computer and Information Science
Volume2735 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference5th International Workshop on Big Data Driven Edge Cloud Services, BECS 2025 and 3rd International Workshop on the Semantic WEb of EveryThing, SWEET 2025, co-located with 25th International Conference on Web Engineering, ICWE 2025
Country/TerritoryNetherlands
CityDelft
Period25.06.3025.07.3

Keywords

  • Edge-cloud system
  • Just-in-time defect prediction
  • Large Language Model

Fingerprint

Dive into the research topics of 'PROPER-SDP: PROmpt-Based Project Evolution-awaRe Software Defect Prediction for Edge-Cloud Systems'. Together they form a unique fingerprint.

Cite this