An Architectural Technical Debt Index Based on Machine Learning and Architectural Smells - A novel approach to estimate architectural technical debt principal

Aug 5, 2026

Upload by Finn

Technical debt (TD) management depends on measuring the principal effort already accumulated in software systems, yet architectural TD estimation remains insufficiently automated, freely available, and thoroughly validated. The study proposes an approach that predicts the severity of an architectural smell using a learning-to-rank machine learning model and statically counts the exact lines of code responsible for each smell. A case study and 16 practitioner interviews evaluate representativeness, with 71% agreement on refactoring effort.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages28

Reading Time1 h 11 min

AccessFree to download

Introduction

Technical debt principal and interest

Proposed approach

Learning-to-rank severity estimation

Static code analysis for smell-related lines of code

Combining severity and code evidence to compute principal

Validation and study design

Case study and practitioner interviews

University of Groningen An Architectural Technical Debt Index Based on Machine Learning and Architectural Smells Sas, Darius; Avgeriou, Paris Published in: IEEE Transactions on Software Engineering DOI: 10.1109/TSE.2023.3286179 IMPORTANT NOTE: You are advised to consult the publisher's version (publisher's PDF) if you wish to cite from it. Please check the document version below. Document Version Publisher's PDF, also known as Version of record Publication date: 2023 Link to publication in University of Groningen/UMCG research database Citation for published version (APA): Sas, D. , & Avgeriou, P. (2023) . An Architectural Technical Debt Index Based on Machine Learning and Architectural Smells. IEEE Transactions on Software Engineering , 49(8), 4169-4195. [https://doi.org/10.1109/TSE.2023.3286179](https://doi.org/10.1109/TSE.2023.3286179) Copyright Other than for strictly personal use, it is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license (like Creative Commons) . The publication may also be distributed here under the terms of Article 25fa of the Dutch Copyright Act, indicated by the “Taverne” license. More information can be found on the University of Groningen website: [https://www.rug.nl/library/open-access/self-archiving-pure/taverne](https://www.rug.nl/library/open-access/self-archiving-pure/taverne)amendment. Take-down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim. Downloaded from the University of Groningen/U MCG research database (Pure): [http://www.rug. nl/research/portal. For technical reasons the](http://www.rug. nl/research/portal. For technical reasons the)[ ](http://www.rug. nl/research/portal. For technical reasons the)[number of authors shown on this cover page is limited to 10 maximum.](number of authors shown on this cover page is limited to 10 maximum.) Download date: 04-08-2026 An Architectural Technical Debt Index Based on Machine Learning and Architectural Smells Darius Sas and Paris Avgeriou Abstract—A key aspect of technical debt (TD) management is the ability to measure the amount of principal accumulated in a system. The current literature contains an array of approaches to estimate TD principal, however, only a few ofthem focus speciﬁcallyon architectural TD, but none of them satisﬁes all three of the following criteria: being fully automated, freely available, and thoroughly validated. Moreover, a recent study has shown that many of the current approaches suffer from certain shortcomings, such as relying on hand-picked thresholds. In this article, we propose a novel approach to estimate architectural technical debt principal based on machine learning and architectural smells to address such shortcomings. Our approach can estimate the amount of technical debt principal generated by a single architectural smell instance. To do so, we adopt novel techniques from Information Retrieval to train a learning-to-rank machine learning model(more speciﬁcally, a gradient boosting machine) that estimates the severity of an architectural smell and ensure the transparency of the predictions. Then, for each instance, we statically analyse the source code to calculate the exact number of lines of code creating the smell. Finally, we combine these two values to calculate the technical debt principal. To validate the approach, we conducted a case study and interviewed 16 practitioners, from both open source and industry, and asked them about their opinions on the TD principal estimations for several smells detected in their projects. The results show that for 71% of instances, practitioners agreed that the estimations provided were representative of the effort necessary to refactor the smell. Index Terms

FAQs

What problem does the paper address in technical debt management?

It targets measuring the principal effort of architectural technical debt, which prior approaches inadequately estimate under requirements such as full automation, free availability, and thorough validation.

How does the approach estimate architectural technical debt principal?

It predicts smell severity using a learning-to-rank machine learning model, then performs static source-code analysis to count lines of code creating the smell, combining both signals into the principal estimate.

How was the proposed method validated and what were the results?

Validation used a case study with 16 practitioners from open source and industry, assessing estimates for smells in their projects; for 71% of instances, practitioners agreed the estimates reflected refactoring effort.

Aug 5, 2026

Upload by Finn