Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206818,
        author = {Aishwarya K. Suvarna and Subhramanya Bhat},
        title = {Explainable AI Framework for Transparent Machine Learning Decision-Making},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {566-571},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206818},
        abstract = {Artificial intelligence (AI) technologies are becoming more popular in areas like health care, banking, and risk assessment for informed and precise decision-making processes. However, many machine learning algorithms have become “black boxes,” making the rationale for decision-making challenging to comprehend. Inefficiencies in explaining the rationale for decision-making have led to significant ethical issues concerning trust, responsibility, fairness, and legal compliance, especially when the decision-making process has far-reaching consequences. Explainable artificial intelligence (XAI) technology can overcome such inefficiencies by providing comprehensible rationales for AI-based decision-making processes. The proposed study develops a framework for XAI, which facilitates transparent decision-making processes using machine learning. They assist stakeholders in gaining insights into how certain input characteristics contribute to certain outputs, increasing their confidence and allowing them to make decisions accordingly. The proposed approach can be used in many different industries, including healthcare and financial services, because it allows for better transparency in tasks such as disease diagnostics, fraud detection, and risk management. It also ensures that the application of AI is ethically acceptable and that any bias present is easily identifiable.},
        keywords = {Explainable Artificial Intelligence, Decision Transparency, Machine Learning, Model Interpretability, Responsibility.},
        month = {July},
        }