A Survey of Algorithm Debt in Machine and Deep Learning Systems: Definition, Smells, and Future Work

ACM Computing Surveys 2026 Open access

Read full text
Authors: Emmanuel Iko-Ojo Simon, Chirath Hettiarachchi, Fatemeh H. Fard, Alex Potanin, Hanna Suominen
DOI: 10.1145/3806391
Cited by: 1
References: 48

Abstract

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.

Fields of Study & Subjects

Machine Learning and Data Classification Adversarial Robustness in Machine Learning Advanced Neural Network Applications

Publication details

Journal / source
ACM Computing Surveys
Publisher
Association for Computing Machinery (ACM)
Volume
58
Issue
11
Pages
1–35
Publication date
2 April 2026
Language
EN