A Churchill-Inspired Metaheuristic Optimization Algorithm: CIRSO (Churchillian Resilience & Strategy Optimizer)

Abstract

This paper proposes a new metaheuristic optimizer inspired by Winston Churchill’s strategic leadership attributes: resilience under adversity, coalition-building,
disciplined yet adaptive decision-making, and the ability to “rally” effort when progress stalls. We translate these attributes into algorithmic operators that combine
(i) persistence against stagnation, (ii) cabinet-style multi-policy exploration, (iii) coalition fusion around elite solutions, and (iv) morale-boost “rally steps” that
intensify local exploitation near promising regions. The proposed method—CIRSO—is evaluated on a convex quadratic test problem ???? = (???? − 3)
2 + (???? − 2)
2

and five standard benchmark functions. A complete Python implementation (NumPy + Matplotlib only) is provided with multiple graphical outputs (colored
convergence curves, 2D contours with trajectories, 3D surface paths, and multi-run statistics). The results show that Churchill-inspired operators can improve
robustness against premature convergence while maintaining competitive convergence speed.