Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Interpretable Machine-Learning Approach in Estimating FDI Inflow: Visualization of ML Models with LIME and H2O

Interpretable Machine-Learning Approach in Estimating FDI Inflow: Visualization of ML Models with... AbstractIn advancement of interpretable machine learning (IML), this research proposes local interpretable model-agnostic explanations (LIME) as a new visualization technique in a novel informative way to analyze the foreign direct investment (FDI) inflow. This article examines the determinants of FDI inflow through IML with a supervised learning method to analyze the foreign investment determinants in Hungary by using an open-source artificial intelligence H2O platform. This author used three ML algorithms—general linear model (GML), gradient boosting machine (GBM), and random forest (RF) classifier—to analyze the FDI inflow from 2001 to 2018. The result of this study shows that in all three classifiers GBM performs better to analyze FDI inflow determinants. The variable value of production in a region is the most influenced determinant to the inflow of FDI in Hungarian regions. Explanatory visualizations are presented from the analyzed dataset, which leads to their use in decision-making. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Baltic Journal of European Studies de Gruyter

Interpretable Machine-Learning Approach in Estimating FDI Inflow: Visualization of ML Models with LIME and H2O

Baltic Journal of European Studies , Volume 11 (1): 20 – May 1, 2021

Loading next page...
 
/lp/de-gruyter/interpretable-machine-learning-approach-in-estimating-fdi-inflow-0ESbOJZ9UP
Publisher
de Gruyter
Copyright
© 2021 Devesh Singh, published by Sciendo
ISSN
2228-0596
eISSN
2674-4619
DOI
10.2478/bjes-2021-0009
Publisher site
See Article on Publisher Site

Abstract

AbstractIn advancement of interpretable machine learning (IML), this research proposes local interpretable model-agnostic explanations (LIME) as a new visualization technique in a novel informative way to analyze the foreign direct investment (FDI) inflow. This article examines the determinants of FDI inflow through IML with a supervised learning method to analyze the foreign investment determinants in Hungary by using an open-source artificial intelligence H2O platform. This author used three ML algorithms—general linear model (GML), gradient boosting machine (GBM), and random forest (RF) classifier—to analyze the FDI inflow from 2001 to 2018. The result of this study shows that in all three classifiers GBM performs better to analyze FDI inflow determinants. The variable value of production in a region is the most influenced determinant to the inflow of FDI in Hungarian regions. Explanatory visualizations are presented from the analyzed dataset, which leads to their use in decision-making.

Journal

Baltic Journal of European Studiesde Gruyter

Published: May 1, 2021

Keywords: FDI; H2O; local interpretable model-agnostic explanations; machine learning

There are no references for this article.