Multi-Criteria Comparison as a Method of Advancing Knowledge-Guided Machine Learning

arXiv:2403.11840v1 Announce Type: new
Abstract: This paper describes a generalizable model evaluation method that can be adapted to evaluate AI/ML models across multiple criteria including core scientific principles and more practical outcomes. Emerging from prediction competitions in Psychology and Decision Science, the method evaluates a group of candidate models of varying type and structure across multiple scientific, theoretic, and practical criteria. Ordinal ranking of criteria scores are evaluated using voting rules from the field of computational social choice and allow …

abstract arxiv comparison competitions core cs.lg decision evaluation knowledge machine machine learning ml models multiple paper practical prediction psychology science scientific type