A Comparative Study of Explainable Artificial Intelligence Techniques for Interpreting Machine Learning Models
IOSR Journal of Computer Engineering · 2026-06 · 28 (6) · 63-74
DOI: 10.9790/0661-2806016374 ↗Kurz gefasst
Fachartikel in der Zeitschrift IOSR Journal of Computer Engineering, 2026-06. Verfasst von Jyoti Dahiya.
Abstract (Originalsprache)
The use of Artificial Intelligence (AI) and Machine Learning (ML) is becoming more and more widespread in healthcare, education, finance, and decision-making. Although they have increased significance, most machine learning models generate predictions without a clear explanation of how they come up with such predictions. This non-transparency may render such AI-based decisions challenging to comprehend, analyze, and accept. Explainable Artificial Intelligence (XAI) overcomes this issue as it offers details of the factors that affect the model predictions. This study based on the comparative analysis of two popular XAI methods: Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). The paper will examine how these techniques elucidate machine learning predictions, single out significant features, and assist in explaining model behavior. The machine learning models will be utilized in experiments through chosen machine learning models and appropriate datasets. Their explanations will be contrasted based on the aspects of consistency, interpretability, computation performance, and utility to predict model behavior. The results will be used to show the strengths and weaknesses of each method and under what circumstances any technique can be more advantageous than the other. This study will help justify the choice of proper explanation strategies and will also help create more transparent and reliable machine learning systems.
Zitieren
APA
Dahiya, J. (2026). A Comparative Study of Explainable Artificial Intelligence Techniques for Interpreting Machine Learning Models. IOSR Journal of Computer Engineering, 28(6), 63-74. https://doi.org/10.9790/0661-2806016374
Vancouver
Dahiya J. A Comparative Study of Explainable Artificial Intelligence Techniques for Interpreting Machine Learning Models. IOSR Journal of Computer Engineering. 2026;28(6):63-74. doi:10.9790/0661-2806016374
BibTeX
@article{Dahiya2026,
author = {Dahiya, Jyoti},
title = {A Comparative Study of Explainable Artificial Intelligence Techniques for Interpreting Machine Learning Models},
journal = {IOSR Journal of Computer Engineering},
year = {2026},
volume = {28},
number = {6},
pages = {63--74},
doi = {10.9790/0661-2806016374}
}
EUVIMED