A Survey of Algorithm Debt in Machine and Deep Learning Systems: Definition, Smells, and Future Work
The adoption of Machine and Deep Learning (ML/DL) technologies introduces maintenance challenges, leading to Technical Debt (TD). Algorithm Debt (AD) is a TD type that impacts the performance and scalability of ML/DL systems. A review of 42 primary studies expanded AD’s definition, uncovered its implicit presence, identified its smells, and highlighted future directions. These findings will guide an AD-focused study, enhancing the reliability of ML/DL systems.
Authors
- Chirath Hettiarachchi (ORCID: https://orcid.org/0000-0002-7702-0718)
- Fatemeh H. Fard (ORCID: https://orcid.org/0000-0002-4505-6257)
- Alex Potanin (ORCID: https://orcid.org/0000-0002-4242-2725)
- Hanna Suominen (ORCID: https://orcid.org/0000-0002-4195-1641)
- Emmanuel Iko-Ojo Simon (ORCID: https://orcid.org/0000-0002-8494-6885)
Institutions
- Australian National University (AU)
- University of British Columbia (CA)
- University of Turku (FI)
- Laboratoire d'Informatique de Paris-Nord (FR)
Publication Details
- Journal
- ACM Computing Surveys
- Published
- 2026-04-02
- DOI
- https://doi.org/10.1145/3806391
- Primary Topic
- Machine Learning and Data Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00