Large-Scale Patch Recommendation at Alibaba

Xindong Zhang, Chenguang Zhu, Yi Li, Jianmei Guo, Lihua Liu, and Haobo Gu

In Proceedings of the 42nd International Conference on Software Engineering (ICSE), 2020

Abstract: We present PRECFIX, a pragmatic approach targeting large-scale industrial codebase and making recommendations based on previously observed debugging activities. PRECFIX collects defect-patch pairs from development histories, performs clustering, and extracts generic reusable patching patterns as recommendations. Our approach is able to make recommendations within milliseconds and achieves a false positive rate of 22%. PRECFIX has been rolled out to Alibaba to support various critical businesses.

Cite:

@inproceedings{Zhang2020LSP,
  author = {Zhang, Xindong and Zhu, Chenguang and Li, Yi and Guo, Jianmei and Liu, Lihua and Gu, Haobo},
  booktitle = {Proceedings of the 42nd International Conference on Software Engineering (ICSE)},
  month = jun,
  pages = {252--253},
  publisher = {ACM},
  title = {Large-Scale Patch Recommendation at Alibaba},
  year = {2020}
}