Entrepreneurial firm creation and economic uncertainty: an explainable artificial intelligence approach

Through this paper, we examined the relationship between macroeconomic factors and new entrepreneurial firms in France during the 2000–2020 period; this relationship included several uncertainties and shocks (the 9/11, the 2008 global financial crisis, the Brexit, COVID-19 Pandemic, and so forth). To this aim, we applied various advanced machine learning (ML) techniques, including the eXtreme Gradient Boosting (XGBoost) algorithm, Light Gradient-Boosting Machine (LightGBM) algorithm, Neural Network (NN), Random Forest (RF), and Linear Regression (LR). We also investigated SHapley Additive exPlanation (SHAP) framework for interpretation and analysis purposes. Furthermore, we compared the performance and forecasting accuracy of the five models. The study revealed three major results. First, the XGBoost algorithm provides the most accurate prediction of a firm's creation. Second, a heterogeneous relationship exists between new business creation and the business cycle. Third, higher GDP and unemployment levels are associated with greater procyclicality and countercyclicality in entrepreneurship, respectively. Finally, the results of the study suggest the importance of developing effective financial assistance during economic downturns to encourage faster recovery in the formation of new businesses.