The current issue and full text archive of this journal is available on Emerald Insight at:

https://www.emerald.com/insight/2077-1886.htm

Foreign direct investment and local A rational

framework for
interpretable model-agnostic FDI decision
making
explanations: a rational framework
for FDI decision making
Devesh Singh Received 20 May 2021
Revised 5 November 2022
Corvinus Institute for Advanced Studies, Corvinus University of Budapest, 28 July 2023
Budapest, Hungary Accepted 30 September 2023

Abstract
Purpose – This study aims to examine foreign direct investment (FDI) factors and develops a rational
framework for FDI inflow in Western European countries such as France, Germany, the Netherlands,
Switzerland, Belgium and Austria.
Design/methodology/approach – Data for this study were collected from the World development indicators
(WDI) database from 1995 to 2018. Factors such as economic growth, pollution, trade, domestic capital
investment, gross value-added and the financial stability of the country that influence FDI decisions were
selected through empirical literature. A framework was developed using interpretable machine learning (IML),
decision trees and three-stage least squares simultaneous equation methods for FDI inflow in Western Europe.
Findings – The findings of this study show that there is a difference between the most important and trusted
factors for FDI inflow. Additionally, this study shows that machine learning (ML) models can perform better
than conventional linear regression models.
Research limitations/implications – This research has several limitations. Ideally, classification
accuracies should be higher, and the current scope of this research is limited to examining the performance
of FDI determinants within Western Europe.
Practical implications – Through this framework, the national government can understand how investors
make their capital allocation decisions in their country. The framework developed in this study can help
policymakers better understand the rationality of FDI inflows.
Originality/value – An IML framework has not been developed in prior studies to analyze FDI inflows.
Additionally, the author demonstrates the applicability of the IML framework for estimating FDI inflows in Western
Europe.
Keywords FDI, Machine learning, Interpretable machine learning,
Local interpretable model-agnostic explanations
Paper type Research paper

1. Introduction
Foreign investment capital is important for the growth and development of both developing
and developed economies (Nguyen, 2023). Therefore, foreign direct investment (FDI) inflow
and its determinants have been discussed by various researchers in a wide range of contexts
at the national, regional and firm levels (refer to Abu and Karim, 2016; Buckley et al., 2012;
Dinh et al., 2019; Gheorghe and Marian, 2014; Nielsen et al., 2017; Rahman and Shahbaz, 2013;
Singh, 2023). Foreign investors’ decisions on where to invest are based on various parameters

JEL Classification — B17, F21, G11

© Devesh Singh. Published in Journal of Economics, Finance and Administrative Science. Published
by Emerald Publishing Limited. This article is published under the Creative Commons Attribution (CC
BY 4.0) licence. Anyone may reproduce, distribute, translate and create derivative works of this article
Journal of Economics, Finance and
(for both commercial and non-commercial purposes), subject to full attribution to the original publication Administrative Science
and authors. The full terms of this licence maybe seen at http://creativecommons.org/licences/by/4.0/ Emerald Publishing Limited
2077-1886
legalcode DOI 10.1108/JEFAS-05-2021-0069
JEFAS such as geopolitical, social, economic and geographical determinants, which lead to
differences in FDI inflow strategies (Makojevi
c et al., 2016). Analyzing the FDI determinants,
most researchers have focused on the traditional approach, and few have used the smartness
learning approach to intelligence, networking, agility and other machine learning (ML)
algorithms for a deeper analysis of the research problem. Furthermore, this smartness
learning approach has limitations in terms of explainability, interpretability and trust
because of human emotional interference. Driverless artificial intelligence (AI) enhanced
transparency by presenting precise insights into the mechanisms and results of the generated
model and its predictions, and the local interpretable model-agnostic explanation (LIME)
enhanced trustworthiness by providing interpretability.
The ML algorithm is not new for determining the FDI attractiveness. Singh (2023) examined
FDI inflow at the regional level in Hungarian counties using an artificial neural network (ANN)
from 2001 to 2018 and found that the ANN can converge a wide variety of indicators that
influence FDI inflow. The root-mean-square error (RMSE) value confirms that the ANN
algorithm performs better than the general linear model (GLM) for determining FDI inflow.
Meyliana et al. (2018) examined the factors that influence the foreign investment decisions at the
country level, in the methodology, they implemented the classifiers such as a decision trees,
support vector machine (SVM), gradient boosting machine (GBM), nearest neighbor, Gaussian
processes, random forest (RF), neural network (NN), naive Bayes and adaptive boosting (ADA-
boost) through ML algorithm. The results show that foreign companies benefit from the
presence of overseas subsidiaries to minimize risk, and in all classifiers, the decision tree has the
highest accuracy rate of 31.50%. Schneider (2020) identifies the factors affecting the FDI location
selection decision process using a large dataset of 2361 variables from 217 countries and
employs the RF regression model for feature selection and a deep neural network (DNN) to
predict FDI values. The research uses hyper-tuning of parameters to select the hidden layers in
DNN and RMSE benchmarks to measure the performance. The results suggest that the
government should have slowly improved political and economic institutions by implementing
continuous policy reforms, instead of relying on a few statically significant variables. A higher
investment in the global community leads to international prosperity. Devereux and Griffith
(2003) discuss the empirical literature on FDI inflows through a decision tree. In their literature
review, they observed that the decision tree of FDI inflow literature can be classified into three
groups. First, discrete choice examines the location of production or export units. Second, these
studies used individual firm-level data to examine the determinants of FDI. Third, these studies
use the confidential data of firms, mainly examining organizational sentiment for FDI.
A substantial amount of literature has explored different ML models to find the FDI
determinants. Several studies have explored different statistical and ML models for
determining FDI inflows. However, to the best of the author’s knowledge, no prior study has
developed an interpretable machine learning (IML) framework to determine FDI inflow
decisions. Therefore, this study fills this gap and contributes to the literature by developing
an FDI inflow decision framework utilizing the IML, or more specifically, the LIME.
Additionally, the author demonstrates the applicability of the IML framework for estimating
FDI inflows in Western Europe and contributes to rigorous science. This research applies
three robust ML models through LIME using a driverless AI–H2O open-source platform to
explore the FDI determinants. Several efforts were made in this study to accomplish the
research goal. First, the author determines the FDI determinants and presents their global
interpretation to understand their relationship with the prediction target. Second, since the
most important variable of FDI is not the causation of actual FDI inflow, the author depicts
the local interpretation through the LIME. Third, the FDI inflow decision tree is created based
on the trusted variable found through the model-agnostic approach. Finally, we find causality
among the variables using simultaneous equations. The objective of this study is to examine
FDI factors and develop a rational framework to understand foreign investors’ FDI inflow
decisions in Western European countries. Further, this study fills gaps in the literature by A rational
addressing the following question: First, how can ML-based prediction systems play an framework for
important role in investment decisions? Second, the model-agnostic IML approach and LIME
can increase the trust level of foreign investors by creating ML reports. Third, the authors
FDI decision
differentiate and identify the most influential and important variable for FDI inflow in the making
Western Europe (WE) region.
Further, this article propagates in the following sections: 2) a literature review presents
possible covariates and the factors that are most important to investors, 3) data and
descriptive statistics presented in this section, 4) the methodology sectio presents the
econometrics behind the ML, 5) the results and discussion and 6) the conclusion section
presents the limitation, policy implications and future recommendation.

2. Literature review
This section discusses and explores the possible factors related to FDI inflow. Numerous
empirical and scientific articles discuss the determinants of FDI. The author focuses on a
literature review of six factors: environmental pollution, trade, financial accumulation,
gross value-added (GVA), economic growth and the country’s national account financial
stability.

2.1 FDI and environmental pollution

The empirical literature on FDI and environmental pollution can be classified into four
categories. In the first category, it is evident that FDI reduces CO2 emissions in the host
country. Demena and Afesorgbor (2020) conducted FDI and environmental emissions meta-
analyzes of 65 primary studies. The effect of FDI on the environment is almost zero; however,
after heterogeneity, FDI reduces environmental emissions in developed countries compared
with developing countries. This implies that FDI inflow standards in developed countries are
high. Second, the category supports the “pollution haven hypothesis”: FDI inflow
significantly increases the CO2 emission of the host country. Shao (2018) presents the
relationship between FDI and environmental emissions using dynamic panel data and shows
that FDI has a negative impact on carbon emissions in high-income, middle-income and low-
income countries. However, after considering additional factors such as fossil fuels, trade
openness, urbanization and industrial intensity, FDI has a positive impact on environmental
emissions. The third category argues that the “pollution heaven hypothesis is insignificant
practice” which means “pollution heaven” practices are not behavioral in the real world. Zhu
et al. (2016) investigated FDI and CO2 emission through quantile regression and concluded
that FDI has an insignificant impact on low emission countries in low quantile and high
emission countries have a positive impact; therefore, high emission countries pay more
attention to environmental regulation and environmental problems. The fourth category
supports both the “pollution halo” and “pollution-haven hypotheses. This means that FDI and
CO2 emissions have bidirectional causality when FDI causes emission, it supports the “halo
hypothesis” and if emission cause FDI it supports the “pollution haven hypothesis”. Shahbaz
et al. (2018) analyze the environmental degradation effect by accounting for FDI, economic
growth and financial development in France. This result supports the pollution haven
hypothesis of FDI in France: FDI decreases environmental quality by increasing CO2
emissions, while financial development decreases CO2 emissions. Therefore, to achieve the
European Union (EU) target of reducing domestic emissions by 40%, it is necessary to
strengthen the financial sector. Doytch and Uctum (2016) analyze FDI and environmental
effects along globalization and suggest that FDI inflow in services decreases pollution,
supporting the halo hypothesis, while for the manufacturing sector, FDI inflow increases the
pollution effect and supports the negative halo effect. FDI inflow in high-income countries
JEFAS reduces the environmental pollution support halo effect, and in low- and middle-income
countries, FDI inflows increase environmental pollution.

2.2 FDI and trade

Varamini and Kalash (2010) examined the role of FDI in trade balance and economic growth in
European economies using the Granger causality test. This result suggests that economic
growth has unidirectional causality with FDI inflow in emerging European economies, and
there is no negative relationship between FDI and trade imbalance in European economies.
Mitze et al. (2010) found a link between the German trade model and FDI in European countries,
using a simultaneous equation model. Their findings suggest that West Germany and the EU15
have a positive impact on FDI inflows, imports and exports. Similarly, East Germany and the
EU27 countries have a positive impact on FDI inflows, imports and exports. Similarly, East
Germany and the EU27 countries have a positive impact between FDI inflow and, imports and
exports. Nobi et al. (2020) examined the structural changes in the trade flow of different
commodities using the hierarchical organization of the minimum spanning tree (MST). Their
results show that manmade trade commodities are much more hierarchical than natural fuels
such as minerals. Apostolov (2016) found a strong relationship between exports and FDI and
between gross domestic product (GDP) and FDI in Southern Europe. Faeth (2006) tested the
dynamic relationship between FDI, domestic investment, trade (imports and exports) and GDP.
The results show that FDI directly enhances domestic investment and GDP, although GDP and
FDI increase imports and decrease export growth. Furthermore, discounts in tax rates and
lenient trade policies influence foreign investment decisions (Tian, 2018). The corporate tax has
a significant effect on organisation for economic co-operation and development (OECD)
countries from 2001 to 2013, where lower tax rates attract the FDI. Gropp and Kostial (2000)
discussed the corporate tax in the sense of FDI flows and showed that net FDI inflow
significantly affects the EU tax harmonization. They presented that countries, especially
Germany, Italy and Ireland, slash their corporate tax rates as a result FDI inflow to these
countries increased as well as the tax revenue also increased.

2.3 FDI and financial accumulation

According to Amighini et al. (2017), theories suggest that FDI plays an important role in financial
development both indirectly through its impact on capital formation and directly as an external
source of capital. Therefore, FDI and financial accumulation are positively associated. Argiro
(2003) mentions that FDI inflow increases capital formation because it is a source of financing.
Ruxanda and Murare (2010) find that FDI inflows increase gross fixed capital formation through
spillover effects. Kalotay (2010) examined the FDI pattern in Europe and used gross fixed capital
formation as a proxy for financial accumulation. In European regions, the ratio of FDI to fixed
capital formation increases over time and is higher than the world average. Omri and Kahouli
(2014) estimated the relationship between FDI, domestic capital and economic growth and
concluded a unidirectional relationship between FDI and domestic capital formation and
bidirectional causality between domestic capital and GDP. Finally, they concluded that FDI
contributes to domestic capital growth, but the growth of domestic capital does not contribute to
FDI inflow in the Middle East and North Africa region.

2.4 FDI and value-added

Sj€oholm (2016) found that FDI and gross value added are associated with each other; foreign
investment received from firms has a positive effect on value-added in a local firm and
enhances the high level of value-added. Therefore, three main phenomena increase value-
added. First, the foreign firm’s resources bring management, technology and capital and
contribute to improving production. Second, the mechanism is based on the types of goods A rational
and services that are being produced in the host country. FDI might cause structural changes, framework for
such as the expansion from high-value-added manufacturing sectors to high-value service
sectors. Third, technology spillover in the host country attracts foreign firms to invest in the
FDI decision
host country and helps increase the expansion of local firms. FDI can impact value added making
through domestic firms. Similarly, the research by Alvarado et al. (2017) examines the impact
of FDI on economic growth and uses the variables trade, physical capital, GVA in agriculture,
GVA in service and GVA in the manufacturing sector. The results vary according to the
development of countries: FDI has an insignificant effect in upper-middle-income countries,
a negative and significant effect in lower-middle-income countries and a significant and
positive effect on products in high-income countries. Adarov and Stehrer (2019) examine FDI,
capital formation and structural change value chains in Europe. The results show that FDI
constitutes an important driver of trade in value-added and global value chain participation.
Furthermore, in terms of production, foreign-controlled companies and overall gross value
added to the economy are related and improve economic growth (Domesov
a, 2011).

2.5 FDI and national account stability

Abu and Karim (2016) analyzed the relationships among economic growth, FDI, domestic
investment and domestic savings in terms of a national account. The results demonstrate
positive unidirectional causality from FDI to domestic investment and economic growth, and
positive bidirectional causality between domestic investment and domestic savings.
Similarly, Bayer (2014) finds a bidirectional relationship between FDI and gross domestic
investment in the short run. Albulescu et al. (2010) found FDI determinants in Central and
Eastern European regions. Their results show that the financial position of a nation not only
supports investment sustainability but is also a significant determinant of FDI
attractiveness. Overall, the stable financial position of a country plays an important role in
attracting FDI. Mahmood et al. (2018) present that financial stability can be maintained by the
optimal level of institutional development and attract more foreign investors. In the
long-term, FDI and institutional stability are cointegrated and tend to move in the same
direction. Thus, higher institutional stability attracts more FDI. Institutional stability is
exogenous to FDI inflows, whereas FDI endogenously affects institutional stability.
Although substantial methods of FDI inflow have been estimated, the author finds a
literature gap in a robust framework for FDI inflow based on rationality. This study contributes
to the literature on FDI inflow estimations by developing an IML framework for FDI inflows.
Further, the literature indicates that multiple sets of variables determine FDI inflow. Therefore,
this study considered six factors in Western European countries: environmental, trade,
economic growth, financial accumulation, GVA and national account stability. This study fills
this gap in the literature by developing an FDI framework based on IML.

3. Method
3.1 Research design
In recent decades, high-dimensional data and complex variables have become common in
business, economics and finance. Researchers have been using ML algorithms such as artificial,
recurrent and convolution, regularization techniques (ridge, lasso and elastic net), and other ML
classifiers to determine the FDI variables that can influence investors’ investment decisions.
Although the ML model has high accuracy and performance, it may discriminate against traits
and characteristics to maximize the prediction accuracy (Molnar, 2019). Another drawback of
ML methodologies is that they increase accuracy but are difficult for humans to interpret
because of their “black-box” nature. According to a study by Ribeiro et al. (2016), IML
JEFAS algorithms such as LIME have been developed to increase the interpretability of black-box
models. Doshi-V
elez and Kim (2017) explain that the rigorous science of IML can be defined as
the “ability to explain or to present in understandable terms to a human”.
When it comes to predictive modeling instead of what is predicted? A good framework is “why
a prediction was made. However, it reduces the predictive performance (Molnar, 2019). Therefore,
it is important to emphasize trusted variables instead of important variables. Therefore, to find the
most trusted variable for FDI inflow, the LIME algorithm was used. In contemporary LIME tests,
what happens to the prediction when a variation of data feeds to the ML model and generates a
new dataset of permuted samples? With this new dataset, LIME trains an interpretable model
based on the weighted proximity of sampled instances to the instance of interest. ElShawi et al.
(2019) found that the LIME outperforms in mimicking the black-box model and interpreting the
model with accuracy and quality of explanation for tabular data.
Further, LIME helps to understand why ML model classifiers make FDI predictions and
focuses on the training set of the local surrogate model instead of the global surrogate model.
Contemporary LIME tests: what happens to the FDI inflow prediction when the variation of
the dataset is fed to the ML models. To achieve this, LIME generates a new dataset of
permuted samples. With this new dataset, LIME trains an interpretable model based on the
weighted proximity of sampled instances to the instance of interest. The phenomena of LIME
can be understood by the following steps: 1) permutation in LIME means replication of data,
2) similarity distance measure between original and permuted data, 3) generation of models
for outcome prediction, 4) description of the outcome and selection of features, 5) model fit in
permuted data based on the similarity score, and 6) depicting or generating a report based on
feature weight. The FDI inflow estimation algorithm for Western European countries can be
classified into two parts: the objects and the second explainer. Where the object consists of the
FDI feature training data. To create FDI models, interpretable algorithms use the explainer-
object, a type of feature distribution list of the training dataset, and ML models.
The predictive model’s algorithm is given on the GitHub University of Cincinnati, and the
interested reader can find the details on (http://uc-r.github.io/lime). Figure 1 shows the
framework of the FDI analysis.
Figure 1 depicts the FDI inflow decision-making framework. Methodologically, this
research has three main components: open-source H2O, LIME, decision tree implemented
through the ML algorithm and statistical component (simultaneous equation models).

Figure 1.
Framework for FDI
analysis
The FDI inflow framework in this study is based on five steps. First, data were collected from A rational
the WDI database. The second step finds the most important determinant and presents an framework for
individual conditional expectation (ICE) plot to analyze how these variable observations
impacted FDI inflow over time in Western Europe. In the third step, the author analyzed the
FDI decision
FDI determinants through GLM, GBM and RF regression, forwarded this model to LIME and making
generated predictive reports. After describing the FDI inflow factors through the IML.
Fourth, to understand how the FDI variable is involved in the FDI decision process, the
author created a decision tree using Rpart based on the Gini impurity measure split nodes.
A decision tree is useful for classifying variables in terms of the possible paths, nodes and
branches. Within a decision tree, a branch leads to a possible path to follow, and a node
represents the attribute of the variables. The drawback of ML is that it struggles to find
causality among variables. Therefore, at this stage of the framework, there is a shortcoming
because the decision tree and predictive model do not explain the causal relationship among
the variables. To overcome this shortcoming, simultaneous equation models were used.
Therefore, to investigate how causality among these variables affects each other in the
selected period, the author uses the three-stage least squares (3SLS) simultaneous equation
approach to find causation among the variables. Therefore, in the fifth step, after presenting
the most influential variable involved in the decision of FDI inflow in Western Europe, the
author finds the causality among the variables involved in FDI inflow decisions through
3SLS simultaneous equation models. Thus, 3SLS has been used because of its advantages in
that it makes it possible to estimate all the parameters of the model at the same time and
consider a probable correlation between the error terms of the structural form of the model,
which makes it more robust than other simultaneous techniques.

3.2 Data and variables

The data for this study were collected from the world development indicators (WDI) database
from 1995 to 2018. Factors such as economic growth, environmental pollution, trade, domestic
capital investment, GVA and financial stability of the country were selected through empirical
literature. To model these factors, we used proxy variables such as economic growth as a proxy
for real GDP. The other proxies for the variables are presented in Table 1 and the definitions of
the variables are based on the WDI database. The variables used in this study and their details
are listed in Table 1. Because the main merit of LIME is to predict the trusted model related to the
real practical world, instead of predicting the log value that is not behavioral with the real-world
prediction system because log normalizes the time effect, this research predicts the actual value,
which is more accurately related to the practical world. However, to solve the variable’s high
range problem, the author converted the all-variable observation to the current United States
(US) $/million and identified the causality author using a log.
Descriptive statistics and ranges of the variables are shown in Table 2. The descriptive table
shows the mean, median, maximum values and quadrant values. The aggregative tendencies of
the observations are shown as the means. The quartiles in the descriptive statistics represent the
location of an ordered dataset. The first and third quartiles show the data set in 25 percentile
(dataset of lower 25%) and 75 percentiles (dataset of lower 75%).

3.3 Analytical procedures

The methodology used in this research can be expressed by the following econometric
expressions.
3.3.1 General linear model (GLM).
gðEYðyjxÞÞ ¼ β0 þ β1x1 þ . . . βp xp (1)
JEFAS Dimensions Literature support Symbol Variable definition

Foreign direct Dependent variable FDII Net inflows

investment, inward
Environmental Shahbaz et al. (2018), Shao (2018), CO2 Adjusted savings: carbon
Demena and Afesorgbor (2020) dioxide damage
PED Adjusted savings: particulate
emission damage
Trade Cassou (1997), Mitze et al. (2010), EGS Exports of goods and services
Varamini and Kalash (2010)
IGS Imports of goods and services
EBGS External balance on goods
and services
Tax Taxes less subsidies on
products
Economic growth Almfraji and Almsafir (2014) GDP Gross domestic product
Financial accumulation Faeth (2006), Kalotay (2010), GFCF Gross fixed capital formation
Adhikary (2011)
GNE Gross national expenditure
CFC Consumption of fixed capital
FCE Final consumption
expenditure
GCF Gross capital formation
Gross value added Domesov
a (2011), Alvarado et al. GVAM Manufacturing, value added
(2017), Adarov and Stehrer (2019)
AGVA Agriculture, forestry and
fishing, value-added
GVABP Gross value added (GVA) at
basic prices
GVAC Industry (including
construction), value-added
National account Albulescu et al. (2010), Abu and TR Total reserves (includes gold)
financial stability Karim (2016), Mahmood et al. (2018)
GDS Gross domestic savings
CI Changes and stock of
inventories held by firms
Table 1. Note(s): All variables in current US$/million, data source: WDI
Variable description Source(s): Own elaboration

The basic mathematical expression of GLM is given as (Molnar, 2019). Where basically, the
GLM consists of components: g 5 link function, EY 5 distribution from the exponential family.
3.3.2 Random forest (RF). RF is based on the principal Gini index and entropy. The
decision tree can be explained by the following equations (Gaber and Atwal, 2013):
X
C
Gini¼ 1 ðpi Þ2 (2)
i¼1
Where c 5 number of classes and Pi 5 relative frequency of the class.
Entropy determines how the node should branch the forest:
X
C
entropy ¼ −pi *log 2ðpi Þ (3)
i¼1

RF uses the distance of each node from the predicted actual value.
FDII GVABP Tax GDS TR GFCF

Min 361467 Min 175,626 Min 20,983 Min 52,966 Min 11,828 Min 48,933
1st Qu 14,241 1st Qu 384,959 1st Qu 45,719 1st Qu 118,308 1st Qu 23,239 1st Qu 97,102
Median 38,889 Median 1,034,592 Median 119,382 Median 308,490 Median 54,693 Median 246,632
Mean 59,439 Mean 1,319,899 Mean 149,823 Mean 358,514 Mean 72,534 Mean 314,981
3rd Qu 73,038 3rd Qu 2,275,612 3rd Qu 258,815 3rd Qu 552,619 3rd Qu 112,600 3rd Qu 540,060
Max 733,827 Max 3,571,700 Max 392,063 Max 1,099,080 Max 248,856 Max 837,596

EGS CI FCE IGS CO2 GVAM

Min 78,792 Min 24161 Min 143,834 Min 80,519 Min 689.9 Min 35,847
1st Qu 259,640 1st Qu 1377 1st Qu 314,599 1st Qu 237,188 1st Qu 2150 1st Qu 64,046
Median 424,220 Median 4818 Median 846,636 Median 417,765 Median 4683.5 Median 150,875
Mean 559,869 Mean 7793 Mean 1,111,209 Mean 524,124 Mean 6381 Mean 218,740
3rd Qu 740,120 3rd Qu 13,334 3rd Qu 1,932,183 3rd Qu 742,031 3rd Qu 8826.2 3rd Qu 279,788
Max 1,877,740 Max 47,344 Max 2,864,690 Max 1,634,020 Max 25,455.6 Max 795,960

CFC PED GVAC GCF AGVA GDP

Min 31,969 Min 124.3 Min 55,664 Min 49,652 Min 2624 Min 196,800
1st Qu 72,063 1st Qu 268.5 1st Qu 99,986 1st Qu 101,352 1st Qu 4553 1st Qu 431,190
Median 180,632 Median 671.9 Median 246,062 Median 247,156 Median 17,166 Median 1,155,124
Mean 251,921 Mean 950 Mean 327,618 Mean 322,774 Mean 20,503 Mean 1,469,723
3rd Qu 440,552 3rd Qu 1308 3rd Qu 482,781 3rd Qu 558,743 3rd Qu 35,192 3rd Qu 2,519,378
Max 718,884 Max 3153.4 Max 1,085,110 Max 855,359 Max 47,221 Max 3,963,770
Source(s): Own elaboration
making
FDI decision
A rational
framework for

Table 2.
Descriptive statistics
JEFAS X
N
MSE¼ 1=N ðfi  yiÞ2 (4)
i¼1

Where: N 5 number of data points, fi 5 value returned by the model, yi 5 actual value at data
point i.
3.3.3 Gradient boosting machine (GBM). The formulation of GBM is according to
(Friedman, 2001; Natekin and Knoll, 2013).
 
ðρt; θtÞ ¼ argmin −gtðxiÞþρhðxi; θÞ2 (5)
ρ;θ

Where, ρ 5 step size at tth iteration, gt(x) 5 boost increment in the function space, h(x,
θ) 5 base-learner function or new function parallel to the negative gradient, i 5 1 along the
observed data, θ 5 parameter estimates.
3.3.4 Feature importance. Partial dependence plots (PDP) is the better tool to see the feature
importance inside the model. The PDP for regression is expressed according to (Molnar, 2019;
Das and Tsapakis, 2020):
  Z
f xS ðxS Þ ¼ Exc b
b f ðxS ; xC Þ ¼ bf ðxS ; xC ÞdPðxC Þ (6)

XS 5 one or two features of interest and X C 5 other features used in the ML model b
f; XS and
Xc combined the whole features in the ML model.
3.3.5 LIME. Mathematically, the interpretability constraint can be expressed as follows:
explanationðxÞ ¼ argmin Lðf ; g; π x Þ þ UðgÞ (7)
g ∈G

In an equation, x is the model g to minimize the loss function while the model complexity UðgÞ
keeps low. π x defines the neighborhood size around the instances x.
This article uses the three classifiers GBM, RF and GLM. All three models were built with
an open-source ML platform H2O. The performance of the models was measured by the
accuracy parameters such as RMSE and mean absolute error (MAE) etc.
3.3.6 Simultaneous equation model. To estimate the causality among foreign direct
investmen inflow (FDII), gross value added construction (GVAC), particulate emission damage
(PED) and exports of goods and services (EGS) were estimated through the following equation:
 
FDII l_ ¼ f GVAC l_; PEDl_; EGS l;_ (8)
where i 5 1 . . . . . .N, country.
Write the equation in panel form and take the logarithm to attain reliable and consistent
results. Further express the equation in a system of equation form as
lnðFDIIÞit ¼ β0 þ β1 lnðGVACÞit þ β2 lnðPEDÞit þ β3 lnðEGSÞit þ εit (9)
lnðGVACÞit ¼ β0 þ β1 lnðFDIIÞit þ β2 lnðPEDÞit þ β3 lnðEGSÞit þ εit (10)
lnðPEDÞit ¼ β0 þ β1 lnðFDIIÞit þ β2 lnðGVACÞit þ β3 lnðEGSÞit þ εit (11)
lnðEGSÞit ¼ β0 þ β1 lnðFDIIÞit þ β2 lnðGVACÞit þ β3 lnðPEDÞit þ εit (12)

Where the subscript in equations (9) to (12), i 5 1, . . .., N denoted country and t 5 1, . . . . . ., T
is the time period and ε is the error term.
4. Results A rational
The author used an RF plot to identify the most important variables affecting FDI inflow in framework for
Western Europe. To further understand how the response variable FDI inflow changes
according to these identified variables, we used the ICE plot. Because both RF and ICE depict
FDI decision
global interpretation, the author uses LIME to develop the local interpretation model. Figure 2 making
depicts only the ten most important variables for FDI inflow, and Figure 3 depicts how the tax
variable changes across observations.

Figure 2.
Variable importance

Figure 3.
ICE plot to predict FDI
inflow probability by
the tax
JEFAS Figure 2 shows the magnitude of the variables that are most important for FDI inflow in
Western Europe. The first point that emerges from Figure 2 is that tax subsidies on products
are the most important variables for FDI inflow. The tax variable in this research indicates
government subsidies on the current account of enterprises and subsidies on net taxes on
products. According to Darby et al. (2014), industrial activity grows fruitfully in regions where
the government provides tax subsidies. According to Tian (2018), the government should adopt
tax subsidy strategies to attract FDI, where firms are in a position of high risk and high return.
Furthermore, according to Abdioglu et al. (2016), net FDI inflows and taxes have country-
specific effects because the purpose of scaling the tax rate is to lure FDI to accomplish the
country’s economic goal. Furthermore, gross capital formation (GCF) and gross fixed capital
formation (GFCF) are the second and fifth most important variables, respectively. This
indicates that the capital formation in Western Europe is positively associated with FDI inflow.
For example, FDI inflow in the United Kingdom (UK) represented around one-third of the GFCF
in 2006, but it varied according to year. The UK outperformed FDI inflow as a percentage of the
GFC (Munday et al., 2009).
The major drawback of the RF plot representation is that it does not indicate a relationship
with the dependent variable. The RF plot indicates the importance of the independent variable
with respect to that of the dependent variable. Therefore, to further examine how each instance
of FDI inflow is associated with independent features, the author uses an ICE plot. Since it is
difficult to present the ICE plot for all 10 variables in a single manuscript, the author presented
the highly weightage variable only, i.e, tax. The ICE plot for taxes is shown in Figure 3.
Figure 3 shows how the FDI prediction for each instance is associated with the featured
tax. Initially, the FDI inflow probability increased. Therefore, there is a positive relationship
between the FDI prediction value and taxes. According to Agostini et al. (2007), subsidies on
product tax rebates increase FDI inflows in European regions, such as Switzerland, Belgium,
Austria and the Netherlands. The positive and negative relationships between corporate tax
and FDI are similar to those in previous studies Gropp and Kostial (2000) and Cassou (1997).
Once the tax value reaches a certain level, the FDI inflow decreases drastically and
propagates almost in parallel for each instance. This means that increases in taxes decrease
FDI inflows, implying a negative relationship (similar to Gropp and Kostial, 2000; Sato, 2012;
Mudenda, 2015; Abdioglu et al., 2016).
Three models, RF, GLM and GBM, were created, and the accuracy of their model
performance is presented in Table 3. An explanation of this classifier is provided in the
Figure A1. Continuous variables were split into 5 bins (cases). The low value of the RMSE in
Table 3 shows the benchmarking sheet of model performance, and the lowest RMSE value
indicates that the model has better accuracy. In this study, the best-fit ML model was GBM
compared to other ML models and had the lowest RMSE value of 39,584.66.
Although the ML model has high accuracy, it is less trustworthy in the real world because
of its interpretability. Furthermore, a single matrix with such classification accuracy is not
trustworthy because of its incomplete explanation of real-world scenarios (Doshi-V
elez and
Kim, 2017). Figure 4 shows the LIME report generated directly through the ranger RF. The
other prediction models and their performances are presented in the Figure A1.

GLM RF GBM

MSE 9,803,375,237 8,713,714,626 1,566,945,110

RMSE 99,012 93,347.28 39,584.66
Table 3. MAE 56,611.78 41,274.26 17,093.42
Model performance Source(s): Own elaboration
 A rational
framework for
FDI decision
making

Figure 4.
LIME report of FDI
inflow

Figure 4 depicts the most trusted variables in the LIME report. Figure 4: Case 1 has the
highest explanatory fit. From all the cases in Figure 4, GVAC is the most influential factor for
FDI inflow in Western Europe. Trade factor variables such as EGS, IGS and tax;
environmental factor variables such as PED; economic growth factor variables such as real
GDP; domestic capital investment factors such as GCF and GFCF; GVA factor variables such
as GVAC and gross value added manufacturing (GVAM); and financial stability factor
variables such as total reserves (TR) are included in the ten most influential variables. Thus,
all six factors are valuable for FDI inflows in Western Europe. These results are similar to
those of Wojciechowski (2016), who found a long-term relationship between FDI and gross
value added. According to Mart
ınez-Gal
an and Fontoura (2019), after controlling the other
FDI variables, the country’s gross value added contributes positively to FDI inflow. Similarly,
Abdouli and Hammami (2020) suggest that financial and economic policies should focus on
protecting the environment along with economic growth, with a better level of financial
development and FDI inflow. Sastre and Recuero (2019) suggested that the relationship
between domestic investment and FDI depends on the type of industry and has a high
forward integration with the global value chain. According to Faeth (2006) FDI, economic
growth and domestic investment directly influence each other; however, they indirectly
influence the trade variables.
Further, after finding the trusted variables, the author visualizes the variable through a
decision tree to understand the transparent decision-making process of FDI inflow. In the
decision tree algorithm, the author used an 80% training set and a 20% testing set. Figure 5
The first node from the top is the root node showing the mean FDI inflow in Western Europe.
Each node in the decision tree shows the predicted value and percentage of observations. From
Figure 5, it is evident that GVAC plays a more important role than PED, EGS, GCF and EGS in
JEFAS

Figure 5.
FDI decision tree

determining FDI decisions because it shows a direct effect. Countries that have been less than
the 289eþ3 GVAC value tend to decide on an FDI inflow of 51%. According to Ciccone (2002)
gross value added is an important factor in the agglomeration of industries in France, Italy,
Germany, Spain and the UK. Mitze et al. (2010) found that agglomeration forces positively affect
FDI activity in Germany. Furthermore, PED and EGS also play important roles in FDI inflow
decisions. Therefore, if PED ≥1452 directly leads to FDI inflow with evidence of 14%
observation in the leaf of the decision tree, and if PED ≤1452, the decision of FDI inflow tends to
the EGS. This means that foreign investors are influenced by environmental regulations, which
further affect exports in Western European economies, such as Germany (Kordalska and
Olczyk, 2019). The environmental impact on FDI depends on the host country’s domestic and
foreign firms’ technology gap, capital endowment and environmental regulations in France,
Germany, Sweden and the UK (Zugravu-Soilita, 2017). Environmental policy affects the cost of
production and export-oriented FDI. Further, the export-oriented FDI is sensitive to
environmental regulation and then to local-market-orientated FDI; similarly, this is
observable in Figure 5 decision tree in reverse order (Tang, 2015).

5. Discussion
For continuous FDI inflow, a robust framework is necessary for formulating the policies. This
study developed a framework of FDI inflow and utilized the IML to interpret FDI inflow
factors and predictive performances, a decision tree to understand the involvement of
determinants in FDI inflow, and a simultaneous equation to determine causality. The author
used three ML models, GBM, GLM and RF, to find determinants of FDI, used these
determinants in LIME, and generated predictive reports. Finally, the author empirically
tested the relationship between FDI, PED, EGS and GVAC based on the variables involved in
the FDI decision tree. The performance of the models is presented in Table 4, where lower
RMSE and high R2 values represent a better model. Overall, the results indicate that PED,
EGS and GVAC are the most trusted predictors of FDI inflow. Table 5 presents the model
estimated using the simultaneous equation. Three cases of causality exist among the
variables from FDI inflow to PED, GVAC and EGC.
 Austria Belgium France
R2 RMSE χ2 p R2 RMSE χ2 p R2 RMSE χ2 p

FDII 0.20 0.055 9.72 0.02 0.12 0.124 15.72 0.00 0.20 0.044 9.60 0.04
PED 0.86 0.073 297.92 0.00 0.95 0.95 782.47 0.00 0.95 0.044 766.41 0.00
EGC 0.91 0.074 1533.33 0.00 0.93 0.93 474.72 0.00 0.88 0.108 228.46 0.00
GVAC 0.92 0.035 2719.16 0.00 0.95 0.98 1916.43 0.00 0.92 0.310 1380.41 0.00

Germany Netherland Switzerland

R2 RMSE χ2 p R2 RMSE χ2 p R2 RMSE χ2 p

FDII 0.18 0.097 13.16 0.00 0.20 0.565 14.00 0.00 0.20 0.044 6.99 0.04
PED 0.94 0.040 729.18 0.00 0.91 0.039 807.23 0.00 0.90 0.044 766.41 0.00
EGC 0.92 0.128 434.47 0.00 0.84 0.161 156.56 0.00 0.88 0.108 228.46 0.00
GVAC 0.95 0.033 1805.15 0.00 0.91 0.041 1193.71 0.00 0.91 0.031 1380.41 0.00
Note(s): *p < 0.05, **p < 0.01, ***p < 0.001
Source(s): Own elaboration
making
FDI decision
A rational
framework for

performance and
Table 4.

statistics
3SLS model

equation summary
JEFAS Model 1 Model 2 Model 3 Model 4 Model 5 Model 6
Austria Belgium France Germany Netherland Switzerland

logFDII
logPED 0.423** 1.816*** 0.454* 1.039* 7.332** 0.454*
(2.90) (3.54) (2.34) (2.26) (2.81) (2.34)
logEGS 0.423** 0.185 0.00767 0.0419 1.725** 0.00767
(2.90) (0.74) (0.10) (0.28) (2.69) (0.10)
logGVAC 0.946** 2.031* 0.527 0.682 8.890*** 0.527
(2.99) (2.43) (1.85) (1.19) (3.59) (1.85)
cons 9.407*** 23.62*** 9.461*** 11.34*** 24.33* 9.461***
(7.29) (5.54) (5.58) (4.17) (2.19) (5.58)
logPED
logFDII 0.700** 0.212*** 0.441* 0.167* 0.0368** 0.441*
(2.90) (3.54) (2.34) (2.26) (2.81) (2.34)
logEGS 0.927*** 0.298*** 0.206*** 0.247*** 0.0731 0.206***
(9.24) (5.40) (3.61) (7.02) (1.95) (3.61)
logGVAC 2.099*** 1.442*** 1.365*** 1.162*** 0.925*** 1.365***
(12.92) (15.17) (16.05) (17.73) (15.92) (16.05)
cons 1.444* 9.819*** 2.204* 2.342* 3.341*** 2.204*
(0.46) (11.15) (0.89) (2.01) (9.04) (0.89)
logEGS
logFDII 0.700** 0.114 0.0472 0.0716 0.146** 0.0472
(2.90) (0.74) (0.10) (0.28) (2.69) (0.10)
logPED 0.929*** 1.570*** 1.303*** 2.632*** 1.234 1.303***
(9.24) (5.40) (3.61) (7.02) (1.95) (3.61)
logGVAC 2.166*** 3.166*** 2.839*** 3.683*** 2.539*** 2.839***
(30.21) (11.53) (7.38) (13.40) (4.92) (7.38)
cons 1.199* 16.14*** 13.71* 16.47*** 7.473** 13.71*
(0.38) (5.53) (2.17) (4.85) (3.06) (2.17)
logGVAC
logFDII 0.330** 0.100* 0.243 0.0752 0.0453*** 0.243
(2.99) (2.43) (1.85) (1.19) (3.59) (1.85)
logPED 0.443*** 0.609*** 0.648*** 0.799*** 0.941*** 0.648***
(12.92) (15.17) (16.05) (17.73) (15.92) (16.05)
logEGS 0.456*** 0.254*** 0.213*** 0.238*** 0.153*** 0.213***
(30.21) (11.53) (7.38) (13.40) (4.92) (7.38)
Table 5. cons 0.655* 6.077*** 2.413 3.035*** 3.436*** 2.413
System of equation (0.46) (10.70) (1.44) (3.40) (12.05) (1.44)
models for FDII, PED, Note(s): t statistics in parentheses, *p < 0.05, **p < 0.01, ***p < 0.001
EGS and GVAC Source(s): Own elaboration

In the first case, the causality relationship between FDI inflow and GVAC in all six models
Austria, Germany, France, Belgium, the Netherlands and Switzerland are significant, and
there is bidirectional causality between FDI and GVAC in Austria, Belgium and the
Netherlands. Sayari et al. (2018) found a long-run negatively significant relationship between
the value-added component and FDI in Western Europe. The negative impact of FDI in
Western Europe is due to the changing trend in FDI inflow and its determinants due to global
strategic and macroeconomic considerations. However, they also mention that the negative
impact of FDI is exploratory for future research. Sj€oholm (2016) finds a positive relationship
between FDI and value addition. This positive relationship is due to structural changes in
high-value-added activities in the economy over the last two decades. High value-added
enhances investment and increases tax revenue.
 In the second case, the causality relationship between FDI and PED in all models is A rational
significant and has bidirectional negative causality between PED and FDI in Austria, France, framework for
the Netherlands, Switzerland and Germany, and positive bidirectional causality in Belgium.
The negative relationship between PED and FDI inflow means that an increase in FDI results
FDI decision
in a decrease in environmental emissions, which is referred to as the pollution halo making
hypothesis. The positive and negative causality of FDI and PED in Western Europe can be
understood through the contribution of production-based emissions. According to Liu and
Fan (2017) trade emissions to gross production-based emissions in Western Europe account
for more than 20% of direct fossil fuel emissions, while small countries such as Switzerland,
Belgium and Sweden account for more than 50%. Demena and Afesorgbor (2020) find that
FDI on environmental emissions in 65 primary studies is close to zero. However, if we
consider heterogeneity, FDI significantly reduces environmental emissions.
In the third case, the causality relationship between FDI and EGS inflow shows
bidirectional negative causality between FDI and EGS in Austria, Switzerland and the
Netherlands, while for Belgium, France and Germany, it is insignificant. Conconi et al. (2016)
found Western European countries, such as Belgium. Initially, firms may serve the foreign
market by exporting because they are uncertain about their ability to earn profits in the host
market. Thus, FDI is always preceded by exports, and around 90% of companies serve a
foreign market through exports before they start investing in the host country. Finally, the
causality results among FDI, PED, EGC and GVAC are similar to previous studies (Conconi
et al., 2016; Sj€oholm, 2016; Cole et al., 2017; Liu and Fan, 2017; Sayari et al., 2018).

5.1 Theoretical implications

Despite the policy implications for FDI inflows, drafting policy should focus on a rationally
based policy instead of a reason-based policy. A policy based on the traditional statistical
method is limited by the preoccupied assumption and preconceived opinion, which often bias
the investment decision and diverge the FDI allocation. Further, in the advancement of ML,
trusting the model and prediction are two different aspects to understand FDI investment
decisions. A high-performance model does not guarantee that the created model is trustworthy
for the practical world. Therefore, this creates a gap in predicting trustworthy and actual
influencer variables of FDI investment. This can lead to policy failure. Further the policymaker
should have to trust on a true framework that has interpretability, causation and effectiveness
to the real world. This study suggested that the use of rigorous science can bring the rationality
and overcome the biasness in policy making occurred by preoccupied mind.

5.2 Policy implication

In policymaking, the national government can understand through this framework how
investors make capital allocation decisions in their country. The results of this study should
not be used for naı€ve public policymaking. It considers that by focusing only on GVAC, PED
and EGS can win the race of FDI inflow because investment attractiveness is a system that
can also be affected by the other variables. The framework developed in this study can help
policymakers better understand the rationality of FDI inflows.

5.3 Future research agenda and limitation

This study has several limitations. Ideally, the classification accuracy should be higher.
The current scope is limited to examining the performance of FDI determinants within
Western Europe. Moreover, the framework created in this study may be applied in another
regions to test the FDI influencing factors. Since the FDI depends on the overall collective
condition of a friendly business environment. Therefore, the future research may use this
study framework to test the large and another set of variables.
JEFAS 6. Conclusions
This research achieved the following major objectives to determine the FDI determinants
and present their global interpretation to understand their relationship with the prediction
target. The author implemented an ML-based prediction system, which can play an
important role in investment decisions. Further, the author presented a model-agnostic
approach that can increase the trust level of foreign investors by creating IML reports.
Emphasized along with high-accuracy models, a true framework should have
interpretability, causation and effectiveness in the real world. Therefore, the most
influential and important variable of FDI inflow and the causality among the FDII, GVAC,
PED and EGS variables are presented. This study also discusses an extensive literature
review of IML in the field of foreign investment.
The findings of this study show that ML models perform better than conventional linear
regression models. Additionally, research shows that there is a difference between the most
important factors (tax, GCF and PED) and the most trusted factors (PED, EGS and GVAC) for FDI
inflow in Western Europe. Further, from the decision tree, the author visualizes the decision-
making progress of FDI inflow in Western Europe. Furthermore, from the simultaneous equation,
we find bidirectional causality between FDI and GVAC in Austria, Belgium and the Netherlands;
bidirectional negative causality between PED and FDI in Austria, France, the Netherlands,
Switzerland and Germany; positive bidirectional causality for Belgium; and bidirectional negative
causality between FDI and EGS in Austria, Switzerland and the Netherlands.

References
Abdioglu, N., Binis, M. and Arslan, M. (2016), “The effect of corporate tax rate on foreign direct
investment: a panel study for OECD countries”, Ege Akademik Bakis/Ege Academic Review,
Vol. 8 No. 1, pp. 599-610.
Abdouli, M. and Hammami, S. (2020), “Economic growth, environment, FDI inflows, and financial
development in Middle East countries: fresh evidence from simultaneous equation models”,
Journal of the Knowledge Economy, Vol. 11, pp. 479-511, doi: 10.1007/s13132-018-0546-9.
Abu, N. and Karim, M.Z.A. (2016), “The relationships between foreign direct investment, domestic
savings, domestic investment, and economic growth: the case of Sub-Saharan Africa”, Society
and Economy, Vol. 38 No. 2, pp. 193-217, doi: 10.1556/204.2016.38.2.4.
Adarov, A. and Stehrer, R. (2019), “Implications of foreign direct investment, capital formation and its
structure for global value chains”, 170, available at: https://wiiw.ac.at/implications-of-foreign-
direct-investment-capital-formation-and-its-structure-for-global-value-chains-dlp-5103.pdf
Adhikary, B.K. (2011), “FDI, trade openness, capital formation, and economic growth in Bangladesh: a
linkage analysis”, International Journal of Business and Management, Vol. 6 No. 1, pp. 16-28,
doi: 10.5539/ijbm.v6n1p16.
Agostini, C.A., Universidad, I. and Hurtado, A. (2007), “The impact of state corporate taxes on FDI
location”, Public Finance Review, Vol. 35 No. 3, pp. 335-360.
Albulescu, C.T., Briciu, L. and Coroiu, S.I. (2010), “Determinants of foreign direct investment in CEE: the
role of financial stability”, Analele Stiintifice ale Universitatii ‘Alexandru Ioan Cuza’ din Iasi - Stiinte
Economice (1954-2015), Alexandru Ioan Cuza University, Faculty of Economics and Business
Administration, pp. 85-96, available at: https://ideas.repec.org/a/aic/journl/y2010vsep85-96.html
Almfraji, M.A. and Almsafir, M.K. (2014), “Foreign direct investment and economic growth literature
review from 1994 to 2012”, Procedia - Social and Behavioral Sciences, Vol. 129, May, pp. 206-213,
doi: 10.1016/j.sbspro.2014.03.668.
n
ıguez, M. and Ponce, P. (2017), “Foreign direct investment and economic growth in
Alvarado, R., I~
Latin America”, Economic Analysis and Policy, Vol. 56, December, pp. 176-187, doi: 10.1016/j.eap.
2017.09.006.
Amighini, A.A., McMillan, M.S. and Sanfilippo, M. (2017), “FDI and capital formation in developing A rational
economies: new evidence from industry-level data”, 23049, available at: http://www.nber.org/
papers/w23049 framework for
Apostolov, M. (2016), “Effects of foreign direct investments. Evidence from Southeast Europe”,
FDI decision
Cuadernos de Economia, Vol. 39 No. 110, pp. 99-111, doi: 10.1016/j.cesjef.2015.10.003. making
Argiro, M. (2003), “Foreign direct investment and economic growth in the European union”, Journal of
Economic Integration, Vol. 18 No. 4, pp. 689-707.
Bayer, Y. (2014), “Savings, foreign direct investment inflows and economic growth in emerging Asian
economies”, Asian Economic and Financial Review, Vol. 4 No. 8, pp. 1106-1122.
Buckley, P.J., Forsans, N. and Munjal, S. (2012), “Host-home country linkages and host-home country
specific advantages as determinants of foreign acquisitions by Indian firms”, International
Business Review, Vol. 21 No. 5, pp. 878-890, doi: 10.1016/j.ibusrev.2011.10.001.
Cassou, S.P. (1997), “The link between tax rates and foreign direct investment”, Applied Economics,
Vol. 29 No. 10, pp. 1295-1301, doi: 10.1080/00036849700000019.
Ciccone, A. (2002), “Agglomeration effects in Europe”, European Economic Review, Vol. 46 No. 2,
pp. 213-227, doi: 10.1016/S0014-2921(00)00099-4.
Cole, M.A., Elliott, R.J.R. and Zhang, L. (2017), “Foreign direct investment and the environment”,
Annual Review of Environment and Resources, Vol. 42, pp. 465-487, doi: 10.1146/annurev-
environ-102016-060916.
Conconi, P., Sapir, A. and Zanardi, M. (2016), “The internationalization process of firms: from
exports to FDI”, Journal of International Economics, Vol. 99, pp. 16-30, doi: 10.1016/j.jinteco.
2015.12.004.
Darby, J., Ferrett, B. and Wooton, I. (2014), “Regional centrality and tax competition for FDI”, Regional
Science and Urban Economics, Vol. 49, pp. 84-92, doi: 10.1016/j.regsciurbeco.2014.08.006.
Das, S. and 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, doi: 10.1016/j.ijtst.2019.09.004.
Demena, B.A. and Afesorgbor, S.K. (2020), “The effect of FDI on environmental emissions: evidence from
a meta-analysis”, Energy Policy, Vol. 138 No. xxxx, 111192, doi: 10.1016/j.enpol.2019.111192.
Devereux, M.P. and 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, doi: 10.1016/S0313-5926(03)50021-2.
Dinh, T.T., Vo, D.H. and Vo, A.T. (2019), “Foreign direct investment and economic growth in the short
run and long run: empirical evidence from developing countries”, Journal of Risk and Financial
Management, Vol. 176 No. 12, pp. 1-11.
Domesov
a, M. (2011), Analysis of foreign direct investment in the Czech Republic, Acta Universitatis
Agriculturae et Silviculturae Mendelianae Brunensis, Vol. 59 No. 6, pp. 51-62, doi: 10.11118/
actaun201159040051.
Doshi-Velez, F. and Kim, B. (2017), “Towards a rigorous science of interpretable machine learning”,
available at: http://arxiv.org/abs/1702.08608
Doytch, N. and Uctum, M. (2016), “Globalization and the environmental impact of sectoral FDI”,
Economic Systems, Vol. 40 No. 4, pp. 582-594, doi: 10.1016/j.ecosys.2016.02.005.
ElShawi, R., Sherif, Y., Al-Mallah, M. and Sakr, S. (2019), “ILIME: local and global interpretable model-
agnostic explainer of black-box decision”, ADBIS Lecture Notes in Computer Science,
Vol. 11695, pp. 53-68, LNCS, doi: 10.1007/978-3-030-28730-6_4.
Faeth, I. (2006), Consequences of FDI in Australia-Causal Links Between FDI, Domestic Investment,
Economic Growth and Trade, University of Melbourne, Department of Economics, Vol. 977.
Friedman, J. (2001), “Greedy boosting approximation: a gradient boosting machine”, The Annals of
Statistics, Vol. 53 No. 5, pp. 1189-1232, doi: 10.1214/aos/1013203451”.
JEFAS Gaber, M.M. and Atwal, H.S. (2013), “An entropy-based approach to enhancing Random Forests”,
Intelligent Decision Technologies, Vol. 7, pp. 319-327, doi: 10.3233/IDT-130171.
Gheorghe, S. and Marian, T. (2014), “Foreign direct investment models, based on country risk for some
post-socialist central and eastern European economies”, Procedia Economics and Finance,
Vol. 10 No. 14, pp. 249-260, doi: 10.1016/S2212-5671(14)00300-1”.
Gropp, R. and Kostial, K. (2000), “The disappearing tax base: is foreign direct investment (FDI) eroding
corporate income taxes?”, available at: https://ideas.repec.org/p/ecb/ecbwps/200031.html
Kalotay, K. (2010), “Patterns of inward FDI in economies in transition”, Eastern Journal of European
Studies, Vol. 1 No. 2, pp. 55-76.
Kordalska, A. and Olczyk, M. (2019), “Is Germany a hub of Factory Europe for CEE countries? The
sink approach in GVC decomposition”, Vol. 4/2019 No. 56.
Liu, H. and Fan, X. (2017), “Value-added-based accounting of CO2 emissions: a multi-regional input-
output approach”, Sustainability, Vol. 9 No. 2220, pp. 1-18, doi: 10.3390/su9122220.
Mahmood, N., Shakil, M.H., Akinlaso, I.M. and Tasnia, M. (2018), “Foreign direct investment and
institutional stability: who drives whom?”, Journal of Economics, Finance and Administrative
Science, Vol. 24 No. 47, pp. 145-156, doi: 10.1108/JEFAS-05-2018-0048.
Makojevi
c, N., Kosti
c, M. and Puri
c, J. (2016), “Can the state influence FDI regional distribution: the case
of Czech Republic, Hungary, Poland and Serbia”, Industrija, Vol. 44 No. 2, pp. 43-54, doi: 10.5937/
industrija44-9590.
Mart
ınez-Gal
an, E. and Fontoura, M.P. (2019), “Global value chains and inward foreign direct
investment in the 2000s”, The World Economy, Vol. 42 No. 1, pp. 175-196.
Meyliana, Bunyamin, H. and Agustina, L. (2018), “The relationship between country risk and
company performance in Southeast Asia”, Journal of Business and Retail Management
Research, Vol. 12 No. 3, pp. 211-219, doi: 10.24052/jbrmr/v12is03/art-19.
Mitze, T., Alecke, B. and Untiedt, G. (2010), “Trade-FDI linkages in a simultaneous equations system
of gravity models for German regional data”, Economie Internationale, Vol. 122 No. 2,
pp. 121-162, doi: 10.1016/s2110-7017(13)60032-3.
Molnar, C. (2019), “Interpretable machine learning. A guide for making black box models explainable”,
available at: https://christophm.github.io/interpretable-ml-book/
Mudenda, L.D. (2015), “Corporate income tax rate and foreign direct investment”, available at: https://
www.diva-portal.org/smash/get/diva2:845659/FULLTEXT01.pdf
Munday, M., Roberts, A. and Roche, N. (2009), “A review of the economic evidence on the determinants
and effects of foreign direct investment”, Welsh Economy Research Unit, available at: https://www.
gov.wales/sites/default/files/statistics-and-research/2018-12/090617-foreign-direct-investment-en.pdf
Natekin, A. and Knoll, A. (2013), “Gradient boosting machines, a tutorial”, Frontiers in Neurorobotics,
Vol. 7, DEC, doi: 10.3389/fnbot.2013.00021.
Nguyen, V.B. (2023), “The role of digitalization in the FDI – income inequality relationship in
developed and developing countries”, Journal of Economics, Finance and Administrative
Science, Vol. 28 No. 55, doi: 10.1108/JEFAS-09-2021-0189.
Nielsen, B.B., Asmussen, C.G. and Weatherall, C.D. (2017), “The location choice of foreign direct
investments: empirical evidence and methodological challenges”, Journal of World Business,
Vol. 52 No. 1, pp. 62-82, doi: 10.1016/j.jwb.2016.10.006.
Nobi, A., Lee, T.H. and Lee, J.W. (2020), “Structure of trade flow networks for world commodities”,
Physica A: Statistical Mechanics and its Applications, Vol. 556, October, 124761, doi: 10.1016/j.
physa.2020.124761.
Omri, A. and Kahouli, B. (2014), “The nexus among foreign investment, domestic capital and economic
growth : empirical evidence from the MENA region”, Research in Economics, Vol. 68 No. 3,
pp. 257-263, doi: 10.1016/j.rie.2013.11.001.
Rahman, M.M. and Shahbaz, M. (2013), “Do imports and foreign capital inflows lead economic A rational
growth? Cointegration and causality analysis in Pakistan”, South Asia Economic Journal,
Vol. 14 No. 1, pp. 59-81, doi: 10.1177/1391561413477941”. framework for
Ribeiro, M.T., Singh, S. and Guestrin, C. (2016), “‘Why should i trust you?’ Explaining the
FDI decision
predictions of any classifier”, Proceedings of the ACM SIGKDD International Conference on making
Knowledge Discovery and Data Mining, pp. 1135-1144, 13-17-Augu, doi: 10.1145/2939672.
2939778.
Ruxanda, G. and Murare, A. (2010), “FDI and economic growth.Evidence from simultanious equation
model”, Romanian Journal of Economic Forecasting, Vol. 13 No. 1, pp. 45-58.
Sastre, T. and Recuero, L.H. (2019), Domestic and Foreign Investment in Advanced Economies. The
Role of Industry Integration.
Sato, T. (2012), “Empirical analysis of corporate tax and foreign direct investment”, Policy Research
Institute, Ministry of Finance, Japan, Public Policy Review, Vol. 8 No. 1, pp. 1-20.
Sayari, N., Sari, R. and Hammoudeh, S. (2018), “The impact of value added components of GDP and
FDI on economic freedom in Europe”, Economic Systems, Vol. 42 No. 2, pp. 282-294, doi: 10.1016/
j.ecosys.2017.03.003.
Schneider, J. (2020), “Dislocations in foreign direct investment: a machine learning approach to
identifying over and under-invested international markets”, Doctoral dissertation, Harvard
University.
Shahbaz, M., Nasir, M.A. and Roubaud, D. (2018), “Environmental degradation in France: the effects of
FDI, financial development, and energy innovations”, Energy Economics, Vol. 74, August,
pp. 843-857, doi: 10.1016/j.eneco.2018.07.020.
Shao, Y. (2018), “Does FDI affect carbon intensity? New evidence from dynamic panel analysis”,
International Journal of Climate Change Strategies and Management, Vol. 10 No. 1, pp. 27-42,
doi: 10.1108/IJCCSM-03-2017-0062.
Singh, D. (2023), “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, Vol. 43 No. 4, pp. 542-552, doi: 10.1504/
IJBIS.2023.132806.
Sj€oholm, F. (2016), “Foreign direct investment and value added in Indonesia”, IFN Working Paper.
Tang, J. (2015), “Testing the pollution haven effect: does the type of FDI matter?”, Environmental and
Resource Economics, Vol. 60 No. 4, pp. 549-578, doi: 10.1007/s10640-014-9779-7.
Tian, Y. (2018), “Optimal policy for attracting FDI: investment cost subsidy versus tax rate reduction”,
International Review of Economics and Finance, Vol. 53, pp. 151-159, doi: 10.1016/j.iref.2017.
10.018.
Varamini, H. and Kalash, S. (2010), “Foreign direct investment inflows, economic growth , and trade
balances: the experience of the new members of the European union”, Journal of East West
Business, Vol. 16 No. 1, pp. 4-23, doi: 10.1080/10669860903558102.
Wojciechowski, L. (2016), “The impact of FDI on gross value added in host country with
particular emphasis on manufacturing sector”, Studies of the Industrial Geography
Commission of the Polish Geographical Society, Vol. 30 No. 1, pp. 143-158, doi: 10.24917/
20801653.301.10.
Zhu, H., Duan, L., Guo, Y. and Yu, K. (2016), “The effects of FDI, economic growth and energy
consumption on carbon emissions in ASEAN-5: evidence from panel quantile regression”,
Economic Modelling, Vol. 58, pp. 237-248, doi: 10.1016/j.econmod.2016.05.003.
Zugravu-Soilita, N. (2017), “How does foreign direct investment affect pollution? Toward a better
understanding of the direct and conditional effects”, Environmental and Resource Economics,
Vol. 66 No. 2, pp. 293-338, doi: 10.1007/s10640-015-9950-9.
 JEFAS

Figure A1.
LIME models
rf glm gbm
Appendix

Case: 1 Case: 1 Case: 1

Prediction: 12036.0144384766 Prediction: 61437.3124429551 Prediction: 2117.07903407005
Explanation Fit: 0.117 Explanation Fit: 0.15 Explanation Fit: 0.100
GDS <= 84564 EGS <= 179355 EGS <= 179355
198 < PED <= 251 IGS <= 166912 CO2 <= 1571
GVAC <= 84167 CO2 <= 1571 GVAC <= 84167
GCF <= 74705 GDS <= 84564 GCF <= 74705
IGS <= 166912 FCE <= 233303 198 < PED <= 251
GFCF <= 72469 4096 < AGVA <= 5883 21584 < TR <= 24862
GVABP <= 283602 GNE <= 305224 4096 < AGVA <= 5883
GNE <= 305224 21584 < TR <= 24862 GDP <= 317100
CO2 <= 1571 GVAC <= 84167 2194 < CInv <= 3819
EGS <= 179355 GDP <= 317100 GVABP <= 283602

Case: 2 Case: 2 Case: 2

Prediction: 10534.0378125 Prediction: 61437.6028453355 Prediction: 3954.02468226341
Explanation Fit: 0.106 Explanation Fit: 0.15 Explanation Fit: 0.089
GDS <= 84564 EGS <= 179355 EGS <= 179355
GVAC <= 84167 IGS <= 166912 CO2 <= 1571
PED <= 198 CO2 <= 1571 GVAC <= 84167
GCF <= 74705 4096 < AGVA <= 5883 PED <= 198
IGS <= 166912 GDS <= 84564 GCF <= 74705
GFCF <= 72469 GCF <= 74705 24862 < TR <= 36367
CO2 <= 1571 24862 < TR <= 36367 GNE <= 305224
GNE <= 305224 GVABP <= 283602 4096 < AGVA <= 5883
GVABP <= 283602 GNE <= 305224 GDP <= 317100
FCE <= 233303 759 < CInv <= 2194 FCE <= 233303

Case: 3 Case: 3 Case: 3

Prediction: 9451.38023925781 Prediction: 61437.5573711958 Prediction: 9433.52983687309
Explanation Fit: 0.106 Explanation Fit: 0.14 Explanation Fit: 0.094
PED <= 198 EGS <= 179355 EGS <= 179355
GVAC <= 84167 IGS <= 166912 CO2 <= 1571
GDS <= 84564 CO2 <= 1571 PED <= 198
GCF <= 74705 3342 < AGVA <= 4096 GCF <= 74705
IGS <= 166912 21584 < TR <= 24862 GVAC <= 84167
GFCF <= 72469 PED <= 198 21584 < TR <= 24862
CO2 <= 1571 GDS <= 84564 3342 < AGVA <= 4096
GVABP <= 283602 GCF <= 74705 GNE <= 305224

Feature
Feature
Feature

EGS <= 179355 GVABP <= 283602 GDP <= 317100

GDP <= 317100 CFC <= 54978 Tax <= 34665

Case: 4 Case: 4 Case: 4

Prediction: 8368.94110351562 Prediction: 61437.7579099883 Prediction: 12093.2624752322
Explanation Fit: 0.097 Explanation Fit: 0.15 Explanation Fit: 0.088
GCF <= 74705 EGS <= 179355 EGS <= 179355
GVAC <= 84167 IGS <= 166912 GVAC <= 84167
GDS <= 84564 CO2 <= 1571 PED <= 198
IGS <= 166912 759 < CInv <= 2194 CO2 <= 1571
PED <= 198 GDS <= 84564 GCF <= 74705
GFCF <= 72469 PED <= 198 GDP <= 317100
CO2 <= 1571 GVABP <= 283602 3342 < AGVA <= 4096
GVABP <= 283602 CFC <= 54978 GNE <= 305224
EGS <= 179355 Tax <= 34665 CFC <= 54978
GNE <= 305224 GVAC <= 84167 FCE <= 233303

Case: 5 Case: 5 Case: 5

Prediction: 12414.8868847656 Prediction: 61437.8230434608 Prediction: 25813.3063871661
Explanation Fit: 0.111 Explanation Fit: 0.16 Explanation Fit: 0.094
GDS <= 84564 EGS <= 179355 EGS <= 179355
GCF <= 74705 IGS <= 166912 CO2 <= 1571
GVAC <= 84167 CO2 <= 1571 15664 < TR <= 21584
IGS <= 166912 GNE <= 305224 PED <= 198
PED <= 198 GDS <= 84564 GVAC <= 84167
GFCF <= 72469 3342 < AGVA <= 4096 GCF <= 74705
CO2 <= 1571 2889 < FDII <= 12140 3342 < AGVA <= 4096
GNE <= 305224 GDP <= 317100 GDP <= 317100
GVABP <= 283602 15664 < TR <= 21584 2194 < CInv <= 3819
EGS <= 179355 GFCF <= 72469 GVABP <= 283602
–20000 –10000 0 10000 20000 30000 –8 –4 0 –40000 –20000 0 20000

Weight Weight Weight

Positive Negative Positive Negative Positive Negative

Source(s): Own elaboration

About the author A rational
Dr Devesh Singh obtained his Bachelor in Electronic and Communication Engineering from Dehradun
Institute of Technology in 2010, Master in Business Administration from Center for Development of framework for
Advance Computing in 2014 and PhD from Kaposvar University, Hungary in 2019. He is a former FDI decision
research fellow in Indian Council of Social Science and Research (ICSSR) and Corvinus Institute for making
Advanced Studies. Devesh Singh can be contacted at: [email protected]

For instructions on how to order reprints of this article, please visit our website:
www.emeraldgrouppublishing.com/licensing/reprints.htm
Or contact us for further details: [email protected]