A Taxonomy of Explainability Techniques in AI: Comparative Analysis and Applications Across Domains

Ashish Semwal; Manmohan Singh Rauthan; Deepak Singh Nijwala; Pradeep Rana; Nisha Pokhriyal; Ashish Joshi

doi:10.2991/978-94-6463-872-1_21

<Previous Article In Volume

Next Article In Volume>

A Taxonomy of Explainability Techniques in AI: Comparative Analysis and Applications Across Domains

Authors

Ashish Semwal¹^{, *}, Manmohan Singh Rauthan², Deepak Singh Nijwala¹, Pradeep Rana¹, Nisha Pokhriyal⁴, Ashish Joshi³

¹HNBGU (A Central University), Srinagar Garhwal, Uttarakhand, India, 246174

²UTU, Dehradun, India, 248001

³Graphic Era University, Dehradun, India, 248001

⁴THDC-IHET, Tehri, Uttarakhand, India, 249124

^*Corresponding author. Email: ash.semwal@gmail.com

Corresponding Author

Ashish Semwal

Available Online 4 November 2025.

DOI: 10.2991/978-94-6463-872-1_21 How to use a DOI?
Keywords: Explainable AI; XAI; AI techniques; machine learning; interpretability; comparative analysis; applications
Abstract: The demand for explainability in artificial intelligence (AI) models has grown in relevance as AI keeps invading many spheres of human life. Techniques and approaches aiming at making AI systems and their actions more comprehensible and interpretable to humans are known as explainable artificial intelligence (XAI). This work gives a thorough taxonomy of explainability strategies in artificial intelligence along with a comparative study of the most often used approaches and emphasizes their uses in many fields. The study investigates the advantages, disadvantages, and trade-offs connected with these approaches as well as their applicability to fields like law, banking, healthcare, and autonomous cars. We want to assist academics and practitioners in choosing the most appropriate explanation strategies for their artificial intelligence models by offering a thorough investigation of different approaches and their pragmatic uses.
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the 2nd International Conference on Sustainable Business Practices and Innovative Models (ICSBPIM-2025)
Series: Advances in Economics, Business and Management Research
Publication Date: 4 November 2025
ISBN: 978-94-6463-872-1
ISSN: 2352-5428
DOI: 10.2991/978-94-6463-872-1_21 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Ashish Semwal
AU  - Manmohan Singh Rauthan
AU  - Deepak Singh Nijwala
AU  - Pradeep Rana
AU  - Nisha Pokhriyal
AU  - Ashish Joshi
PY  - 2025
DA  - 2025/11/04
TI  - A Taxonomy of Explainability Techniques in AI: Comparative Analysis and Applications Across Domains
BT  - Proceedings of the 2nd International Conference on Sustainable Business Practices and Innovative Models (ICSBPIM-2025)
PB  - Atlantis Press
SP  - 297
EP  - 315
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-872-1_21
DO  - 10.2991/978-94-6463-872-1_21
ID  - Semwal2025
ER  -

download .riscopy to clipboard