Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning Approach

We examine the main effects of ICT penetration and the shadow economy on sovereign credit ratings and the cost of debt, along with possible second-order effects between the two variables, on a dataset of 65 countries from 2001 to 2016. The paper presents a range of machine-learning approaches, inclu...

Full description

Bibliographic Details
Main Authors: Apostolos Kotzinos, Vasilios Canellidis, Dimitrios Psychoyios
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Computation
Subjects:
Online Access:https://www.mdpi.com/2079-3197/11/5/90
_version_ 1827741720168628224
author Apostolos Kotzinos
Vasilios Canellidis
Dimitrios Psychoyios
author_facet Apostolos Kotzinos
Vasilios Canellidis
Dimitrios Psychoyios
author_sort Apostolos Kotzinos
collection DOAJ
description We examine the main effects of ICT penetration and the shadow economy on sovereign credit ratings and the cost of debt, along with possible second-order effects between the two variables, on a dataset of 65 countries from 2001 to 2016. The paper presents a range of machine-learning approaches, including bagging, random forests, gradient-boosting machines, and recurrent neural networks. Furthermore, following recent trends in the emerging field of interpretable ML, based on model-agnostic methods such as feature importance and accumulated local effects, we attempt to explain which factors drive the predictions of the so-called ML black box models. We show that policies facilitating the penetration and use of ICT and aiming to curb the shadow economy may exert an asymmetric impact on sovereign ratings and the cost of debt depending on their present magnitudes, not only independently but also in interaction.
first_indexed 2024-03-11T03:50:06Z
format Article
id doaj.art-c62d8a92f9904134a5db70d53982ce1c
institution Directory Open Access Journal
issn 2079-3197
language English
last_indexed 2024-03-11T03:50:06Z
publishDate 2023-04-01
publisher MDPI AG
record_format Article
series Computation
spelling doaj.art-c62d8a92f9904134a5db70d53982ce1c2023-11-18T00:58:03ZengMDPI AGComputation2079-31972023-04-011159010.3390/computation11050090Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning ApproachApostolos Kotzinos0Vasilios Canellidis1Dimitrios Psychoyios2Department of Industrial Management, University of Piraeus, 107 Deligiorgi Str., 18534 Piraeus, GreeceDepartment of Industrial Management, University of Piraeus, 107 Deligiorgi Str., 18534 Piraeus, GreeceDepartment of Industrial Management, University of Piraeus, 107 Deligiorgi Str., 18534 Piraeus, GreeceWe examine the main effects of ICT penetration and the shadow economy on sovereign credit ratings and the cost of debt, along with possible second-order effects between the two variables, on a dataset of 65 countries from 2001 to 2016. The paper presents a range of machine-learning approaches, including bagging, random forests, gradient-boosting machines, and recurrent neural networks. Furthermore, following recent trends in the emerging field of interpretable ML, based on model-agnostic methods such as feature importance and accumulated local effects, we attempt to explain which factors drive the predictions of the so-called ML black box models. We show that policies facilitating the penetration and use of ICT and aiming to curb the shadow economy may exert an asymmetric impact on sovereign ratings and the cost of debt depending on their present magnitudes, not only independently but also in interaction.https://www.mdpi.com/2079-3197/11/5/90credit ratingssovereign debtshadow economyNRI indexCARTrandom forest
spellingShingle Apostolos Kotzinos
Vasilios Canellidis
Dimitrios Psychoyios
Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning Approach
Computation
credit ratings
sovereign debt
shadow economy
NRI index
CART
random forest
title Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning Approach
title_full Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning Approach
title_fullStr Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning Approach
title_full_unstemmed Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning Approach
title_short Informal Sector, ICT Dynamics, and the Sovereign Cost of Debt: A Machine Learning Approach
title_sort informal sector ict dynamics and the sovereign cost of debt a machine learning approach
topic credit ratings
sovereign debt
shadow economy
NRI index
CART
random forest
url https://www.mdpi.com/2079-3197/11/5/90
work_keys_str_mv AT apostoloskotzinos informalsectorictdynamicsandthesovereigncostofdebtamachinelearningapproach
AT vasilioscanellidis informalsectorictdynamicsandthesovereigncostofdebtamachinelearningapproach
AT dimitriospsychoyios informalsectorictdynamicsandthesovereigncostofdebtamachinelearningapproach