Modeling cybersecurity investment and development trade-offs using random forest for energy-efficient software engineering

As industrial sectors become increasingly software-driven, balancing cybersecurity, energy efficiency, and profitability is criti- cal in a shifting threat landscape. Despite rising security investments, the interplay between development strategies and energy- constrained operations remains poorly understood. This study examines how software development decisions and security invest- ments affect energy consumption and firm profitability through a simulation of two strategies: Firm A emphasizes energy-saving code reuse, while Firm B pursues performance through new code development. Using a synthetic dataset of 1,000 observations based on realistic parameters such as code volume, security level, and cost, Random Forest Regression predicts energy consump- tion, while sensitivity analysis assesses profit outcomes across varying security investments. Results show that Firm A benefits from long-term profitability at higher security levels, while Firm B’s profits decline due to rising costs and limited demand elastic- ity. These findings underscore the need for firms to balance security spending with energy and development strategies. The paper contributes a simulation-based framework to support secure, energy-efficient software engineering as part of sustainable digital transformation.