Open Access
Research Article
Explainability and interpretability in AI : Bridging the gap between accuracy and transparency
*Sai Prashanth MallelluCorresponding authorsaiprashanth08@ieee.orgSymbiosis Institute of Technology Hyderabad Campus Symbiosis International UniversityPune, Hyderabad, 509217, India0009-0002-1271-816XView full profile → , V. Uma Maheswariumamaheswariv1184@gmail.comDepartment of Computer Science and Engineering Chaitanya Bharathi Institute of TechnologyHyderabad, Telangana, 500075, India0000-0001-8258-9987View full profile → , Anitha Patilpanitha243@gmail.comDepartment of Computer Science and Engineering Koneru Lakshmaiah Education FoundationHyderabad, Telangana, 500045, IndiaView full profile → , Morarjee Kollamorarjeek@gmail.comDepartment of Computer Science and Engineering Chaitanya Bharathi Institute of TechnologyHyderabad, Telangana, 500075, IndiaView full profile → , B. Prasanalakshmidrsana@ieee.orgDepartment of Computer Science King Khalid University Abha, 61421, Saudi Arabia0000-0002-6882-2233View full profile → , Linda Elzubir Gasm Alsidlynda@kku.edu.saDepartment of Computer Science College of Computer Science King Khalid UniversityAbha, 61421, Saudi ArabiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 10 Dec 2024
- Published Online:
- 01 Sep 2025
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2025
- Pages:
- 1963–1971
Abstract
With more sophisticated computational models increasingly used in decision-making, the requirement for transparency in models has accelerated. Explainability and interpretability are at the forefront of guaranteeing complex models are comprehensible, trustworthy, and responsibly used. Explainability is concerned with giving insights into how decisions are made, while interpretability guarantees users can understand why a model makes certain predictions. This work takes into account the need to balance precision with intelligibility in a variety of applications, especially in high-stakes domains like medicine, finance, and engineering. A variety of approaches to enhancing interoperability are discussed, and their implications for ethical and regulatory requirements. Bridging the gap between precision and intelligibility will allow us to construct more trustworthy and accountable computational systems that are aligned with human values and expectations.
Keywords
Subject Classifications
68T0768T0568T09
References
[1] F. Rezaei and M. F. Nia, “Rotational entropy of an annular iterated functions system,” J. Dyn. Syst. Geom. Theories, vol. 19, no. 2, pp. 189–202 (2021).[2] T. K. Mohammed, D. N. Vasundhara, S. H. Mehanoor, E. Sreedevi, P. R. Kumar, C. Manihass, and S. F. Baba, “A novel fusion approach for advancement in crime prediction and forecasting using hybridization of ARIMA and recurrent neural networks,” Journal of Information Systems Engineering and Management, vol. 10, no. 38, pp. 404–420 (2025).[3] A. A. Abbas and Z. M. Sallal, “Hybrid biometric authentication for banks security improvements,” J. Discrete Math. Sci. Cryptogr., vol. 28, no. 4-A, pp. 1037–1050 (2025).[4] T. He and N. Lia, “Age-structured model with varied contact patterns and vaccination of COVID-19 in Liaoning Province, China,” Journal of Statistics and Management Systems, vol. 27, no. 8, pp. 1525–1539 (2024).[5] P. R. Kumar, B. Shilpa, and R. K. Jha, “BrainTract: segmentation of white matter fiber tractography and analysis of structural connectivity using hybrid convolutional neural network,” Neuroscience, vol. 580, pp. 218–230 (2025).[6] B. Shilpa, P. R. Kumar, and R. K. Jha, “LoRa DL: A deep learning model for enhancing the data transmission over LoRa using autoencoder,” The Journal of Supercomputing, vol. 79, pp. 17079–17097 (2023).[7] P. R. Kumar, B. Shilpa, R. K. Jha, and S. N. Mohanty, “A novel end-to-end approach for epileptic seizure classification from scalp EEG data using deep learning technique,” International Journal of Information Technology, vol. 15, pp. 4223–4231 (2023).[8] Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, and Dino Pedreschi, “A survey of methods for explaining black box models,” ACM Comput. Surveys (CSUR), vol. 51, no. 5, pp. 1–42 (2018).[9] N. Arivazhagan, K. Somasundaram, G. B. Mohammad, P. R. Kumar, K. Vijayakumar, and P. Dhavachelvan, “Cloud-Internet of Health Things (IoHT) task scheduling using hybrid moth flame optimization with deep neural network algorithm for e-healthcare systems,” Scientific Programming, vol. 2022, art. 4100352, pp. 1–12 (2022).[10] G. B. Mohammad, Shitharth, and P. R. Kumar, “Integrated machine learning model for URL phishing detection,” International Journal of Grid and Distributed Computing, vol. 14, no. 1, pp. 513–529 (2021).[11] A. Barredo Arrieta, N. Díaz-Rodríguez, J. Del Ser, A. Bennetot, S. Tabik, A. Barbado, S. Garcia, S. Gil-Lopez, D. Molina, R. Benjamins, R. Chatila, and F. Herrera, “Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Inf. Fusion, vol. 58, pp. 82–115 (2020).[12] P. R. Kumar, “Wireless mobile charger using inductive coupling,” Journal of Emerging Technologies and Innovative Research, vol. 5, no. 10, pp. 40–44 (2018).[13] M. B. Khan and A. K. J. Saudagar, “Comparative analysis of medical knowledge and inferential capabilities of modern LLMs,” Journal of Statistics and Management Systems, vol. 27, no. 8, pp. 1713–1722 (2024).[14] R. Q. Abdulkadhim, H. S. Abdullah, and M. J. Hadi, “Improving cryptocurrency price prediction through advanced LSTM-based deep learning techniques,” Journal of Statistics and Management Systems, vol. 27, no. 8, pp. 1701–1712 (2024).[15] B. Shilpa, P. R. Kumar, and R. K. Jha, “Spreading factor optimization for interference mitigation in dense indoor LoRa networks,” in Proc. IEEE IAS Glob. Conf. Emerg. Technol. (GlobConET), pp. 1–5 (2023).
Views: 111Downloads: 11Citations: 0
