Abstract Expedient design choices in software development can lead to Technical Debt (TD), with development teams documenting such decisions as Self-Admitted TD (SATD). Algorithm Debt (AD) is a type of TD resulting from the suboptimal implementation of algorithms, which impacts system performance. Given the impact of AD, its automated detection is crucial in Deep Learning (DL) frameworks due to their complexity and evolution. Early detection of AD in DL frameworks can help mitigate model degradation and scalability issues. Despite previous studies on the automated detection of TD from SATD using Machine Learning (ML)/DL models, research on AD detection in DL frameworks remains underexplored. In this study, we empirically investigated the performance of ML/DL models for the automated detection of AD using a dataset of 38, 881 SATD comments from seven DL frameworks. We trained, evaluated, and tested ML/DL models, used embeddings from both DL and large language models, and explored an approach to enrich the dataset with handcrafted features based on AD-related keywords. Our findings reveal that AD is frequently misclassified as Design or Implementation Debt. Logistic Regression (an ML model) with Custom AD Features, achieved an F1-score of 54% for AD, outperforming other ML/DL models (42% to 52%), highlighting the importance of tailored feature engineering. Our research advances automated AD detection in DL frameworks by providing insights into the strengths and limitations of ML/DL models, serving as a first step to guide future tool development. This could help developers using DL frameworks to identify AD issues during development, thereby enhancing system reliability by mitigating model degradation and scalability challenges.

Technical Debt (TD) is the implied cost of additional rework caused by choosing easier solutions in favour of shorter release time. It impacts software maintainability and evolvability, manifesting as different types (e.g., Code, Test, Architecture). Algorithm Debt (AD) is a new TD type recently identified as sub-optimal implementations of algorithm logic in scientific and Artificial Intelligence (AI) software. Given its newness, AD and its impact on AI-driven software remains a research gap. This poster aims to motivate reflective discussion on AD in AI software, by summarising findings, discussing its possible impact, and outlining future areas of work.