The impact of multinationality on firm value: A comparative analysis of machine learning techniques

Cemil Kuzey, Ali Uyar, Dursun Delen

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

In this study, the impact of multinationality (as measured by foreign sales ratio) and fourteen other financial indicators on firm value (characterized by market capitalization and market-to-book ratio) for the period of 1997-2011 was investigated using two popular machine learning techniques: decision trees and artificial neural networks. We divided the time period of 1997-2011 into two periods; 1997-2004 and 2005-2011 to investigate the robustness of results pre- and post-IFRS implementation. To determine the relative importance of factors as the predictors of firm value, first, a number of classification models are developed; then, the information fusion based sensitivity analysis is applied to these classification models to identify the ranked order of the independent variables. Among the independent variables, multinationality was found to determine firm value only moderately. In addition to multinationality, other financial characteristics such as firm size (as measured by natural logarithm of assets), leverage, liquidity, and profitability were consistently found to be affecting firm value.

Original languageEnglish
Pages (from-to)127-142
Number of pages16
JournalDecision Support Systems
Volume59
Issue number1
DOIs
StatePublished - 1 Mar 2014
Externally publishedYes

Fingerprint

Learning systems
Decision Trees
Information fusion
Decision trees
Sensitivity analysis
Profitability
Sales
Neural networks
Machine Learning
Multinationality
Firm value
Machine learning
Comparative analysis
Comparative Analysis
International Financial Reporting Standards

Keywords

  • Artificial neural networks
  • Decision trees
  • Firm value
  • Machine learning
  • Multinationality
  • Predictive analytics
  • Sensitivity analysis

Cite this

@article{9b77c050fea649928fef222289c2fa35,
title = "The impact of multinationality on firm value: A comparative analysis of machine learning techniques",
abstract = "In this study, the impact of multinationality (as measured by foreign sales ratio) and fourteen other financial indicators on firm value (characterized by market capitalization and market-to-book ratio) for the period of 1997-2011 was investigated using two popular machine learning techniques: decision trees and artificial neural networks. We divided the time period of 1997-2011 into two periods; 1997-2004 and 2005-2011 to investigate the robustness of results pre- and post-IFRS implementation. To determine the relative importance of factors as the predictors of firm value, first, a number of classification models are developed; then, the information fusion based sensitivity analysis is applied to these classification models to identify the ranked order of the independent variables. Among the independent variables, multinationality was found to determine firm value only moderately. In addition to multinationality, other financial characteristics such as firm size (as measured by natural logarithm of assets), leverage, liquidity, and profitability were consistently found to be affecting firm value.",
keywords = "Artificial neural networks, Decision trees, Firm value, Machine learning, Multinationality, Predictive analytics, Sensitivity analysis",
author = "Cemil Kuzey and Ali Uyar and Dursun Delen",
year = "2014",
month = "3",
day = "1",
doi = "10.1016/j.dss.2013.11.001",
language = "English",
volume = "59",
pages = "127--142",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",
number = "1",

}

The impact of multinationality on firm value : A comparative analysis of machine learning techniques. / Kuzey, Cemil; Uyar, Ali; Delen, Dursun.

In: Decision Support Systems, Vol. 59, No. 1, 01.03.2014, p. 127-142.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The impact of multinationality on firm value

T2 - A comparative analysis of machine learning techniques

AU - Kuzey, Cemil

AU - Uyar, Ali

AU - Delen, Dursun

PY - 2014/3/1

Y1 - 2014/3/1

N2 - In this study, the impact of multinationality (as measured by foreign sales ratio) and fourteen other financial indicators on firm value (characterized by market capitalization and market-to-book ratio) for the period of 1997-2011 was investigated using two popular machine learning techniques: decision trees and artificial neural networks. We divided the time period of 1997-2011 into two periods; 1997-2004 and 2005-2011 to investigate the robustness of results pre- and post-IFRS implementation. To determine the relative importance of factors as the predictors of firm value, first, a number of classification models are developed; then, the information fusion based sensitivity analysis is applied to these classification models to identify the ranked order of the independent variables. Among the independent variables, multinationality was found to determine firm value only moderately. In addition to multinationality, other financial characteristics such as firm size (as measured by natural logarithm of assets), leverage, liquidity, and profitability were consistently found to be affecting firm value.

AB - In this study, the impact of multinationality (as measured by foreign sales ratio) and fourteen other financial indicators on firm value (characterized by market capitalization and market-to-book ratio) for the period of 1997-2011 was investigated using two popular machine learning techniques: decision trees and artificial neural networks. We divided the time period of 1997-2011 into two periods; 1997-2004 and 2005-2011 to investigate the robustness of results pre- and post-IFRS implementation. To determine the relative importance of factors as the predictors of firm value, first, a number of classification models are developed; then, the information fusion based sensitivity analysis is applied to these classification models to identify the ranked order of the independent variables. Among the independent variables, multinationality was found to determine firm value only moderately. In addition to multinationality, other financial characteristics such as firm size (as measured by natural logarithm of assets), leverage, liquidity, and profitability were consistently found to be affecting firm value.

KW - Artificial neural networks

KW - Decision trees

KW - Firm value

KW - Machine learning

KW - Multinationality

KW - Predictive analytics

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84897657052&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2013.11.001

DO - 10.1016/j.dss.2013.11.001

M3 - Article

AN - SCOPUS:84897657052

VL - 59

SP - 127

EP - 142

JO - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

IS - 1

ER -