Assessment of Operational Effectiveness Based on Stacking Integrated Learning and Case Reasoning

Abstract

With the advancement of intelligent warfare, the accurate evaluation of combat system effectiveness is crucial for informed combat decision-making. Given the subjectivity and inefficiency associated with traditional artificial combat effectiveness evaluation methods, this paper proposes an evaluation approach based on Stacking ensemble learning and case reasoning. First, an efficiency evaluation index system is developed, utilizing historical evaluation data and the entropy weight-TOPSIS method to gather expert assessments of combat effectiveness, thereby forming an evaluation case. Next, an integrated feature selection model is established to analyze the importance of various indicators, using Stacking ensemble learning to evaluate operational effectiveness. Finally, the effectiveness of this approach is validated through a case study of operational effectiveness assessment.