EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable Artificial Intelligence for Intelligent Decision Support: Integrating Machine Learning and Multi-Criteria Decision Analysis

Kamlesh Gautam, Ms. Suman Punia, Shalini Rawat, M. Govardhan Reddy, Sanjay Sharma, Kumar Debi Prasad

Computer and Decision Making: An International Journal · 06.11.2026 · 3 (8S) · 22-33

DOI: 10.1922/comdem.v3i8s.19112 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer and Decision Making: An International Journal, online erschienen am 06.11.2026. Verfasst von Kamlesh Gautam und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence is becoming more and more part of decisions support; however, making a decision based on predictive performance is not enough when decisions are required to be understandable, contestable and to serve several objectives. In this narrative review, we cover the connection between machine learning (ML), explainable artificial intelligence (XAI) and multi-criteria decision analysis (MCDA) for transparent and actionable intelligent decision making. The paper reviews the development of ML-enabled decision support, the key approaches of XAI, and the main principles of MCDA, and examines the different ways in which the two have been integrated, where explanations for predictions are offered before alternatives are considered in light of criteria and preferences. The literature of hybrid methods from various fields including healthcare, manufacturing, supply chains, environmental management, finance and infrastructure demonstrates that hybrid methods can enhance traceability and structure complex choices, but also that they entail risks such as propagation of uncertainty, instability of explanation, subjectivity of weights and misconversion of predictive importance to decision preference. One main claim is that the complementary roles of ML, XAI, and MCDA are to make predictions, explanations, and evaluations in structured ways. Future systems should thus maintain these distinctions, and provide human oversight, sensitivity analysis, fairness analysis, and feedback. The obtained perspectives put the explainability in the middle of the spectrum as a functional link between predictive intelligence and accountable multi-criteria decision support.

Zitieren

APA

Gautam, K., Punia, M. S., Rawat, S., Reddy, M. G., Sharma, S., & Prasad, K. D. (2026). Explainable Artificial Intelligence for Intelligent Decision Support: Integrating Machine Learning and Multi-Criteria Decision Analysis. Computer and Decision Making: An International Journal, 3(8S), 22-33. https://doi.org/10.1922/comdem.v3i8s.19112

Vancouver

Gautam K, Punia MS, Rawat S, Reddy MG, Sharma S, Prasad KD. Explainable Artificial Intelligence for Intelligent Decision Support: Integrating Machine Learning and Multi-Criteria Decision Analysis. Computer and Decision Making: An International Journal. 2026;3(8S):22-33. doi:10.1922/comdem.v3i8s.19112

BibTeX
@article{Gautam2026,
  author = {Gautam, Kamlesh and Punia, Ms. Suman and Rawat, Shalini and Reddy, M. Govardhan and Sharma, Sanjay and Prasad, Kumar Debi},
  title = {Explainable Artificial Intelligence for Intelligent Decision Support: Integrating Machine Learning and Multi-Criteria Decision Analysis},
  journal = {Computer and Decision Making: An International Journal},
  year = {2026},
  volume = {3},
  number = {8S},
  pages = {22--33},
  doi = {10.1922/comdem.v3i8s.19112}
}
Kostenlos starten →