SEMTRA: Global Semantic Transition and Rough-Set Rules for Auditable Post-Hoc Explainability
Machine Learning and Knowledge Extraction, Vol. 8, No. 7, Article 181
Editorial summary
SEMTRA converts a trained model’s internal features into human-readable attributes and rules. The audit reports where rules apply, conflict, match the model or cannot support a conclusion. Tests across datasets show how these results change with the data and evaluation protocol. The original predictor remains unchanged.
Bibliographic reference
Use the publisher’s record for the citation format required by your journal or organisation.
Pavlo Radiuk, Oleksander Barmak, Iurii Krak. "SEMTRA: Global Semantic Transition and Rough-Set Rules for Auditable Post-Hoc Explainability". Machine Learning and Knowledge Extraction, Vol. 8, No. 7, Article 181, 2026. https://doi.org/10.3390/make8070181
Test a method against your business task.
Describe the decision your system needs to support and the data you have. We assess whether a method fits, define a prototype and agree how to measure its quality, response time and operating cost.