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

Singh, Devesh

doi:10.2478/bjes-2021-0009

Abstract

In 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.

References

Abdipour, M.; Younessi-Hmazekhanlu, M.; Ramazani, S. H. R. & Omidi, A. H. (2019), ‘Artificial neural networks and multiple linear regression as potential methods for modeling seed yield of safflower (Carthamus tinctorius L.),’ Industrial Crops and Products, vol. 127(November 2018), pp. 185–194. https://doi.org/10.1016/j.indcrop.2018.10.05010.1016/j.indcrop.2018.10.050
Search in Google Scholar Back to article
Akbari, A.; Ng, L. & Solnik, B. (2021), ‘Drivers of economic and financial integration : a machine learning approach,’ Journal of Empirical Finance, vol. 61, pp. 82–102. https://doi.org/10.1016/j.jempfin.2020.12.00510.1016/j.jempfin.2020.12.005
Search in Google Scholar Back to article
Arel-Bundock, V. (2017), ‘The political determinants of foreign direct investment: a firm-level analysis,’ International Interactions, vol. 43, no. 3, pp. 424–452. https://doi.org/10.1080/03050629.2016.118501110.1080/03050629.2016.1185011
Search in Google Scholar Back to article
Boghean, C. & State, M. (2015), ‘The relation between foreign direct investments (FDI) and labour productivity in the European Union countries,’ Procedia Economics and Finance, vol. 32, no. 15, pp. 278–285. https://doi.org/10.1016/s2212-5671(15)01392-110.1016/S2212-5671(15)01392-1
Search in Google Scholar Back to article
Boudier-Bensebaa, F. (2005), ‘Agglomeration economies and location choice: Foreign direct investment in Hungary,’ Economics of Transition, vol. 13, no. 4, pp. 605–628. https://doi.org/10.1111/j.0967-0750.2005.00234.x10.1111/j.0967-0750.2005.00234.x
Search in Google Scholar Back to article
Bruneckiene, J.; Jucevicius, R.; Zykiene, I.; Rapsikevicius, J. & Lukauskas, M. (2019), ‘Assessment of investment attractiveness in European countries by artificial neural networks: What competences are needed to make a decision on collective well-being?’ Sustainability, vol. 11, no. 24, art. 6892. https://doi.org/10.3390/su1124689210.3390/su11246892
Search in Google Scholar Back to article
Chuku, C.; Simpasa, A. & Oduor, J. (2019), ‘Intelligent forecasting of economic growth for developing economies,’ International Economics, vol. 159, pp. 74–93. https://doi.org/10.1016/j.inteco.2019.06.00110.1016/j.inteco.2019.06.001
Search in Google Scholar Back to article
Cook, D. (2017), Practical Machine Learning with H2O:Powerful, Scalable Techniques for Deep Learning and AI, Sebastopol, CA: O’Reilly Media.
Search in Google Scholar Back to article
Das, S. & Tsapakis, I. (2020), ‘Interpretable machine learning approach in estimating traffic volume on low-volume roadways,’ International Journal of Transportation Science and Technology, vol. 9, no. 1, pp. 76–88. https://doi.org/10.1016/j.ijtst.2019.09.00410.1016/j.ijtst.2019.09.004
Search in Google Scholar Back to article
Devereux, M. P. & Griffith, R. (2003), ‘The impact of corporate taxation on the location of capital: A review,’ Economic Analysis and Policy, vol. 33, no. 2, pp. 275–292. https://doi.org/10.1016/S0313-5926(03)50021-210.1016/S0313-5926(03)50021-2
Search in Google Scholar Back to article
Fazekas, K. (2000), The Impact of Foreign Direct Investment Inflows on Regional Labour Market in Hungary, SOCO Project Paper, no. 77c.
Search in Google Scholar Back to article
Fazekas, K. (2005), ‘Effects of FDI inflows on regional labour market differences in Hungary,’ Économie Internationale, vol. 102 (April 2003), pp. 83–105. https://doi.org/10.3917/ecoi.102.008310.3917/ecoi.102.0083
Search in Google Scholar Back to article
Friedman, J. (2001), ‘Greedy boosting approximation: a gradient boosting machine,’ The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232. https://doi.org/doi:10.1214/aos/101320345110.1214/aos/1013203451
Search in Google Scholar Back to article
Gaber, M. M. & Atwal, H. S. (2013), ‘An entropy-based approach to enhancing Random Forests,’ Intelligent Decision Technologies, vol. 7, no. 4, pp. 319–327. https://doi.org/10.3233/IDT-13017110.3233/IDT-130171
Search in Google Scholar Back to article
Gasanova, A.; Medvedev, A. N. & Komotskiy, E. I. (2017), ‘The assessment of corruption impact on the inflow of foreign direct investment,’ AIP Conference Proceedings, vol. 1836, no. 1. https://doi.org/10.1063/1.498195110.1063/1.4981951
Search in Google Scholar Back to article
Goldstein, A.; Kapelner, A.; Bleich, J. & Pitkin, E. (2015), ‘Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation,’ Journal of Computational and Graphical Statistics, vol. 24, no. 1, pp. 44–65. https://doi.org/10.1080/10618600.2014.90709510.1080/10618600.2014.907095
Search in Google Scholar Back to article
Guyon, I. & Elisseeff, A. (2003), ‘An introduction to variable and feature selection Isabelle,’ Journal of Machine Learning Research, vol. 3, pp. 1157–1182.
Search in Google Scholar Back to article
Hall, P.; Gill, N.; Kurka, M.; Phan, W. & Bartz, A. (2019), Machine Learning Interpretability with H2O Driverless AI: First Edition, Mountain View, CA: H2o.ai Inc. Retrieved from http://docs.h2o.ai [accessed Mar 2021]
Search in Google Scholar Back to article
Heravi, S.; Osborn, D. R. & Birchenhall, C. R. (2004), ‘Linear versus neural network forecasts for European industrial production series,’ International Journal of Forecasting, vol. 20, no. 3, pp. 435–446. https://doi.org/10.1016/S0169-2070(03)00062-110.1016/S0169-2070(03)00062-1
Search in Google Scholar Back to article
Jiménez, A. & Herrero, Á. (2019), ‘Selecting features that drive internationalization of Spanish firms,’ Cybernetics and Systems, vol. 50, no. 1, pp. 25–39. https://doi.org/10.1080/01969722.2018.155801210.1080/01969722.2018.1558012
Search in Google Scholar Back to article
Korgaonkar, C. (2012), ‘Analysis of the impact of financial development on foreign direct investment: a data mining approach,’ Journal of Economics and Sustainable Development, vol. 3, no. 6, pp. 70–79.
Search in Google Scholar Back to article
Lengyel, I.; Vas, Z.; Kano, I. S. & Lengyel, B. (2017), ‘Spatial differences of reindustrialization in a post-socialist economy: manufacturing in the Hungarian counties,’ European Planning Studies, vol. 25, no. 8, pp. 1416–1434. https://doi.org/10.1080/09654313.2017.131946710.1080/09654313.2017.1319467
Search in Google Scholar Back to article
Makojevic, N.; Kostic, M. & Puric, J. (2016), ‘Može li država da utiče na regionalnu distribuciju SDI—primer Češke, Mađarske, Poljske i Srbije’ [Can a state influence FDI regional distribution: the case of the Czech Republic, Hungary, Poland and Serbia], Industrija, vol. 44, no. 2, pp. 43–54. https://doi.org/10.5937/industrija44-959010.5937/industrija44-9590
Search in Google Scholar Back to article
Molnar, C. (2019), Interpretable Machine Learning. A Guide for Making Black Box Models Explainable. Retrieved from https://christophm.github.io/interpretable-ml-book/ [accessed Mar 2021]
Search in Google Scholar Back to article
Munday, M.; Roberts, A. & Roche, N. (2009), A Review of the Economic Evidence on the Determinants and Effects of Foreign Direct Investment, Cardiff: Cardiff Business School & Welsh Economy Research Unit.
Search in Google Scholar Back to article
Na, L. & Lightfoot, W. S. (2006), ‘Determinants of foreign direct investment at the regional level in China,’ Journal of Technology Management in China, vol. 1, no. 3, pp. 262–278. https://doi.org/10.1108/1746877061070493010.1108/17468770610704930
Search in Google Scholar Back to article
Natekin, A. & Knoll, A. (2013), ‘Gradient boosting machines, a tutorial,’ Frontiers in Neurorobotics, vol. 7 (Dec). https://doi.org/10.3389/fnbot.2013.0002110.3389/fnbot.2013.00021388582624409142
Search in Google Scholar Back to article
Ozturk, I. (2001), ‘The role of education in economic development: a theoretical perspective,’ Journal of Rural Development and Administration, vol. 33, no. 1, pp. 39–47. https://doi.org/10.2139/ssrn.113754110.2139/ssrn.1137541
Search in Google Scholar Back to article
Patra, S. (2019), ‘FDI, urbanization, and economic growth linkages in India and China,’ in Socio-Economic Development: Concepts, Methodologies, Tools, and Applications, Hershey, PA: IGI Global, pp. 313–327. https://doi.org/http://doi:10.4018/978-1-5225-7311-1.ch01710.4018/978-1-5225-7311-1.ch017
Search in Google Scholar Back to article
Pekarskiene, I. & Susniene, R. (2015), ‘Features of foreign direct investment in the context of globalization,’ Procedia – Social and Behavioral Sciences, vol. 213, pp. 204–210. https://doi.org/10.1016/j.sbspro.2015.11.42710.1016/j.sbspro.2015.11.427
Search in Google Scholar Back to article
Pratiwi, I. (2016), Clustered Regression Models for Analysis and Prediction of Foreign Direct Investment Inflows, MA thesis in statistics and data mining, Dept. of Computer and Information Science, Linköping University.
Search in Google Scholar Back to article
Ribeiro, M. T.; Singh, S. & Guestrin, C. (2016), ‘“Why should i trust you?” Explaining the predictions of any classifier,’ KDD ’16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13–17 August, pp. 1135–1144. https://doi.org/10.1145/2939672.293977810.1145/2939672.2939778
Search in Google Scholar Back to article
Salike, N. (2016), ‘Role of human capital on regional distribution of FDI in China: new evidences,’ China Economic Review, vol. 37, pp. 66–84. https://doi.org/10.1016/j.chieco.2015.11.01310.1016/j.chieco.2015.11.013
Search in Google Scholar Back to article
Schneider, J. (2020), Dislocations in Foreign Direct Investment: A Machine Learning Approach to Identifying Over- and Under-Invested International Markets Schneider, Second Year Policy Analysis (SYPA), Schneider Economics.
Search in Google Scholar Back to article
Singh, D. (2021a), ‘Cluster space among labor productivity, urbanization, and agglomeration of industries in Hungary,’ Journal of the Knowledge Economy. https://doi.org/https://doi.org/10.1007/s13132-021-00726-910.1007/s13132-021-00726-9
Search in Google Scholar Back to article
Singh, D. (2021b, forthcoming), ‘Comparison between artificial neural network and linear model prediction performance for FDI disparity and the growth rate of companies in Hungarian counties,’ International Journal of Business Information Systems. https://doi.org/10.1504/IJBIS.2020.1003450210.1504/IJBIS.2020.10034502
Search in Google Scholar Back to article
Szántó, I. (2014), ‘Problems of a declining Hungarian birth rate: a historical perspective,’ Journal of the American Hungarian Educators Association, vol. 7, pp. 95–109. https://doi.org/10.5195/ahea.2014.110.5195/AHEA.2014.1
Search in Google Scholar Back to article

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

Abstract

Paradigm

My account