Forecasting Foreign Direct Investment to Sub-Saharan Africa using Arima Model: A Comparative Analysis of Machine Learning Algorithms
Domaine:
socioeconomic
This study examines the factors that influence individual foreign direct investment decisions and predicts using various Artificial Intelligence (A.I.) Algorithms models. The study also gives us an in-depth insight into the dynamics of complex FDI decisions using those A.I. predictive models. We use structural equation modeling in the prescriptive strand. Return on Investment (ROI), Security/Personal Safety, and Investment Facilitation Services significantly affect individual FDI decisions. On predictive strand analysis, we used various Machine Learning models to evaluate the accuracy of predicting classes of individual FDI risk decisions and the ARIMA model for prediction. We find that Random Forest and Ada Boosting Trees have substantial classification accuracies despite the "No free lunch" theorem. The result also indicates that a better prediction could be made by applying multiple classes of FDI inflow decisions rather than binary classes.