<![CDATA[Break-even management is essential for ensuring business sustainability, pricing fairness, and financial accountability, particularly in environments that demand ethical governance. However, conventional break-even analysis is typically static and lacks adaptive optimisation and structured feedback mechanisms. This study aims to develop an AI-based prototype system for optimising break-even variables within an ethical reflective framework that integrates predictive modelling, constrained optimisation, and governance-based feedback. The methodology combines multiple linear regression and exponential smoothing for revenue forecasting, followed by nonlinear optimisation (SLSQP) to minimise time-to-break-even subject to ethical guardrails, including margin floor and price-smoothing constraints. Simulation results show that the prototype improves forecast accuracy (MAPE reduced from 9.45% to 4.87%) and decreases time-to-break-even from 12.4 to 9.8 months (−21%), while reducing deviation variance from 11% to 5.2% through iterative feedback. The novelty lies in embedding ethical accountability constraints into AI-driven optimisation, offering policy implications for transparent pricing, accountable financial planning, and governance-aligned business decision-making.]]>
Copyrights © 2026
