ISSN: -
Abbreviated Title: J Interpretable Explain Mach Learn Syst
Current Issue: Vol 1, Issue 1 (2026)
The Journal of Interpretable and Explainable Machine Learning Systems is an international, peer-reviewed, open access journal published by Transparent Intelligence Publishing. The journal focuses on advancing research and innovation in interpretable machine learning, explainable artificial intelligence, model transparency, and trustworthy AI technologies that support the development of reliable, accountable, and human-understandable machine learning systems.
JIEMLS provides a scientific platform for researchers, engineers, academics, industry professionals, and policymakers to exchange original research findings and applied knowledge in the rapidly evolving field of interpretable and explainable artificial intelligence. The journal addresses the growing need for transparent, accountable, and human-understandable machine learning systems by promoting interdisciplinary research at the intersection of machine learning, human-computer interaction, cognitive science, and AI ethics.
The journal publishes research covering areas such as interpretable machine learning, explainable artificial intelligence, model transparency, causal machine learning, human-AI interaction, responsible AI governance, deep learning interpretability, and trustworthy AI systems. JIEMLS welcomes contributions that develop new methodologies, computational frameworks, technological solutions, and practical applications for improving the transparency, accountability, and interpretability of modern machine learning systems.
All submitted manuscripts undergo an initial editorial assessment followed by a double-blind peer-review process. Editorial decisions are based on scientific quality, originality, methodological rigor, ethical compliance, and relevance to the journal’s aims and scope.
JIEMLS supports open access publishing to facilitate the broad dissemination of scientific knowledge. Accepted articles are made freely available to the research community in accordance with the journal’s copyright and licensing policies, enabling researchers and practitioners worldwide to access and build upon published findings.
Through interdisciplinary and rigorous scholarly communication, the Journal of Interpretable and Explainable Machine Learning Systems aims to contribute to the development of transparent, trustworthy, and human-understandable machine learning systems and support research addressing current and future challenges in AI interpretability and explainability.
The Journal of Interpretable and Explainable Machine Learning Systems is published
Editor-in-Chief
Professor Amir H Gandomi
View all editors
Journal metrics can be a useful tool for readers, as well as for authors who are deciding where to submit their next manuscript for publication. However, any one metric only tells a part of the story of a journal’s quality and impact. Each metric has its limitations which means that it should never be considered in isolation, and metrics should be used to support and not replace qualitative review.
We strongly recommend that you always use a number of metrics, alongside other qualitative factors such as a journal’s aims & scope, its readership, and a review of past content published in the journal. In addition, a single article should always be assessed on its own merits and never based on the metrics of the journal it was published in.
Speed data is updated every six months, based on the prior six months. Speed data is only available where a journal has made more than 10 decisions of that type in the time period. Speed metrics are averages; some manuscripts will take longer than this. Citation metrics are updated annually mid-year. Please note that some journals do not display all of the following metrics.
Content Access: the total number of times articles in the journal were viewed/downloaded by users of Transparent Intelligence Publishing.
Impact Factor: the average number of citations received by articles published in the journal within a two-year window. Only journals in the Clarivate Science Citation Index Expanded (SCIE), Social Sciences Citation Index (SSCI), Arts and Humanities Citation Index (AHCI) and the Emerging Sources Citation Index (ESCI) have an Impact Factor.
Impact Factor Best Quartile: the journal’s highest subject category ranking in the Journal Citation Reports. Q1 = 25% of journals with the highest Impact Factors.
5 Year Impact Factor: the average number of citations received by articles in the journal within a five-year window.
CiteScore (Scopus)†: the average number of citations received by articles in the journal over a four-year period.
CiteScore Best Quartile†: the journal’s highest CiteScore ranking in a Scopus subject category. Q1 = 25% of journals with the highest CiteScores.
SNIP (Source Normalized Impact per Paper): the number of citations per paper in the journal, divided by citation potential in the field.
SJR (Scimago Journal Rank): Average number of (weighted) citations in one year, divided by the number of articles published in the journal in the previous three years.
From submission to first decision: the average (median) number of days for a manuscript submitted to the journal to receive a first decision. Based on manuscripts receiving a first decision in the last six months. This includes manuscripts which are not sent for peer review (desk rejections). Manuscripts which are sent out for review can therefore have a significantly longer wait than this metric indicates.
From submission to first post-review decision: the average (median) number of days for a manuscript submitted to the journal to receive a first decision if it is sent out for peer review. Based on manuscripts receiving a post-review first decision in the last six months.
From acceptance to online publication: the average (median) number of days from acceptance of a manuscript to online publication of the Version of Record. Based on articles published in the last six months.
Acceptance rate: articles accepted for publication by the journal in the previous calendar year as percentage of all papers receiving a final decision.
Transparent Intelligence Publishing