A New Hybrid Approach for Optimizing Sustainable Entrepreneurship Strategies: Leveraging Global Trends and Data-Driven Techniques for Business Growth and Innovation

Abstract

This study investigates the impact of global trends on sustainable entrepreneurship and explores the application of a hybrid optimization approach to optimize business strategies. The research utilizes machine learning models, including Gradient Boosting Regression (GBR) and Random Forest Regression (RF), to predict the influence of economic, technological, environmental, and social trends on business performance metrics such as profitability and sustainability. These predictions are then enhanced by optimization techniques such as Genetic Algorithms (GA) and Simulated Annealing (SA) to develop sustainable entrepreneurship strategies that balance long-term profitability with sustainability goals. The results indicate that GBR and RF offer superior performance in forecasting business outcomes, achieving high R² values and low Mean Squared Error (MSE) in both profitability and sustainability predictions. Furthermore, the hybrid approach, which integrates machine learning with optimization algorithms, significantly outperforms traditional methods, providing more accurate and adaptive strategies for businesses to navigate global trends. This study contributes to the field of sustainable entrepreneurship by offering an innovative framework that businesses can use to optimize their operations while aligning with sustainability objectives. The findings also highlight the role of emerging global trends in shaping business practices, providing valuable insights for entrepreneurs, policymakers, and business leaders looking to foster sustainable growth.