Optimization-Aware Explainable Machine Learning: Algorithms, Metrics and Applications

Dear Colleagues,

Machine learning models are increasingly used in complex decision environments where accuracy alone is insufficient. Decision makers need models that not only perform well but also provide explanations that are stable, consistent, and actionable. Too often, interpretability is treated as an afterthought, an evaluation step performed once a model is chosen. This approach can lead to explanations that are fragile, inconsistent, or misaligned with stakeholder needs.

This Special Issue focuses on optimization-aware explainable machine learning, an approach that treats explanation as a first-class objective in the model development process. In this view, interpretability is not simply measured after the fact but is actively optimized alongside predictive accuracy, fairness, and other performance criteria. Optimization awareness means designing algorithms, model selection processes, and evaluation pipelines that explicitly account for explanation quality and stability throughout the entire machine learning workflow.

We invite contributions that advance the theory, methodology, and applications of optimization-aware explainable machine learning. Topics of interest include, but are not limited to, the following:

• Algorithms that integrate interpretability constraints or objectives directly into training and model selection;
• Stability-focused interpretability metrics and methods for ensuring explanation robustness under data variation;
• Multi-objective optimization strategies balancing accuracy, fairness, and interpretability;
• Evaluation frameworks that embed stakeholder needs into the optimization process;
• Applications in domains where explanation is critical for adoption, such as agriculture, climate science, healthcare, finance, and engineering;
• Comparative analyses and benchmarks of optimization-driven explainability methods.

We also welcome interdisciplinary submissions that connect optimization-aware explainable machine learning with trustworthy AI, human-centered AI, and responsible deployment practices.

This Special Issue will showcase research where optimization is not only a means to improve predictive performance but also a foundation for developing models that are truly worth explaining. By bringing together experts in optimization, machine learning, and application-driven research, we seek to establish a body of work that will define the future of transparent, accountable AI.

Dr. Tamayo-Vera Dania
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• optimization-aware machine learning
• explainable artificial intelligence
• model interpretability
• explanation stability
• multi-objective optimization
• model selection strategies
• trustworthy artificial intelligence
• interpretability metrics
• stakeholder-aligned explanations
• decision support systems