Skip to main content
Have a personal or library account? Click to login
Automatic detection of technical debt in large-scale java codebases: a multi-model deep learning methodology for enhanced software quality Cover

Automatic detection of technical debt in large-scale java codebases: a multi-model deep learning methodology for enhanced software quality

International Journal on Smart Sensing and Intelligent Systems
Volume 18 (2025): Issue 1 (January 2025)
By: ,  ,  ,   and    
Open Access
|Mar 2025
Figures & tables

Figures & Tables

Figure 1:

TD prediction workflow. TD, technical debt.

Table 1:

Comparison of validation metrics

ModelMSERMSE
LSTM0.0033570.057947
GRU0.0054030.073505
RF regressor0.0060930.078061
GB regressor0.0079000.08888

[i] GB, gradient boosting; GRU, gated recurrent unit; LSTM, long short-term memory; RF, random forest; RMSE, root mean squared error.

Figure 2:

Frontend interface of the project. TD, technical debt.

DOI: https://doi.org/10.2478/ijssis-2025-0012 | Journal eISSN: 1178-5608
Journal RSS Feed
Language: English
Submitted on: Jan 10, 2025
Published on: Mar 25, 2025
Published by: International Journal on Smart Sensing and Intelligent Systems
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year
Keywords:
technical debt,
self-admitted technical debt,
machine learning,
random forest,
gradient boosting,
long short-term memory,
gated recurrent unit,
Java codebases,
software engineering,
automated detection
Related subjects:
Engineering,
Introductions and overviews,
Engineering, other

© 2025 Pooja Bagane, Chahak Sengar, Sumedh Dongre, Siddharth Prabhakar, Obsa Amenu Jebessa, published by International Journal on Smart Sensing and Intelligent Systems
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Volume 18 (2025): Issue 1 (January 2025)
Previous article
Next article