Real-time policy optimization in international entrepreneurial ecosystems via digital twin and fuzzy multi-objective optimization
Abstract
This study presents a multi-objective fuzzy optimization model based on digital twin data that provides the ability to simultaneously analyze startup performance indicators and policy intervention costs under uncertainty. The results obtained show that the model has stable convergence in different scenarios and enables ecosystem performance improvement in the range of about 18 to 26% compared to the baseline. Sensitivity analysis also indicates that “digital twin data quality” and “effectiveness of support policies” have the largest contribution to output changes and together explain more than 40% of the fluctuations in the results. The scenario analysis shows that policies such as financial support and mentoring have the greatest impact on startup sustainability and innovation indicators, even under resource constraints. These findings indicate that combining fuzzy structures with reflected digital twin data can provide an efficient, flexible, and reliable framework for designing smart policy interventions in entrepreneurial ecosystems.