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

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

Post on 23-Dec-2016




3 download


  • ue


    Machine learning

    mularausie p- alue,

    fusion based sensitivity analysis is applied to these classication models to identify the ranked order of theindependent variables. Among the independent variables, multinationality was found to determine rm value

    to multinationality, other nancial characteristics such as rm size (as measured

    dies hackgroutigatingaracte

    the attention of theates and potentials ford services with largeis one of those emerg-

    Decision Support Systems 59 (2014) 127142

    Contents lists available at ScienceDirect

    Decision Supp

    .echaracteristics and/or employing a different set of prediction models(statistical or machine learning based) [2,42,57,64,72,89]. Thoughmany of these studies are successful in predicting bankruptcy, they

    ing countries with its fast growing economy and young population.Thus, this study extends the prior work by examining the impact ofmultinationality along with certain rm characteristics on rm valuesuccessful/unsuccessful rms and their potential values [54]. A simplesearch on the topic bankruptcy prediction returns tens of thousandsof studies. A vast majority of these studies differentiate themselvesfrom those of others by using a somewhat unique set of nancial

    corporations. Emerging markets are attractingwhole world due to their current high growth rthe future. They are ideal markets for goods anpopulations and increasing incomes [11]. Turkeyand corporate governance) were among the fundamental dimensionsthat these investigators had focused on.

    Beside directly addressing the rm value, a large number of researchstudies focused on analyzing and potentially predicting bankruptcy asa means to identify characteristics (in term of nancial ratios) of

    ship concentration is higher in the emerging markets, thus the studiesfor rms headquartered in emerging countries could offer a differentresult for the relationship between international diversication andrm value. Berrill and Mannella [11] state that there is an increasinginterest in studies that relate to emerging markets and multinationaloften fall short on identifying and explainingcan be used as determinants of the rm value

    Corresponding author. Tel.: +1 918 594 8283; fax: +E-mail addresses: (C. Kuzey), auya (D. Delen).

    0167-9236/$ see front matter 2013 Elsevier B.V. All ri and non-nancial, adoption of nancialructure, multinationality,

    they may not fully capture the extent to which the degree of interna-tionalization affects rm value in emerging/developing countries. Leeet al. [58] argue that the capital markets are less developed and owner-characteristics (e.g., voluntary disclosuresreporting standards, auditor type, ownership stSensitivity analysisFirm valueMultinationality

    1. Introduction

    In recent years, value relevance stuattention from researchers of diverse baThose studies generally dealtwith investeristics affect rm value. Financial ch 2013 Elsevier B.V. All rights reserved.

    ve attracted considerablends [1,13,31,38,39,65,87].how certainrm charac-

    This study aims to address specically the value relevance ofinternational operations of multinational companies. Previously, somestudies tested the inuence of multinationality on rm value albeitmost of them were in developed countries [35]. While these workshave examined the impact of multinationality in various countries,Articial neural networks by natural logarithm of assets), leverage, liquidity, and protability were consistently found to be affectingrm value.Predictive analyticsDecision trees only moderately. In additionThe impact of multinationality on rm valmachine learning techniques

    Cemil Kuzey a, Ali Uyar a, Dursun Delen b,a Department of Management, Fatih University, Buyukcekmece, Istanbul 34500, Turkeyb Department of Management Science and Information Systems, Spears School of Business, Ok

    a b s t r a c ta r t i c l e i n f o

    Article history:Received 12 November 2012Received in revised form 31 October 2013Accepted 8 November 2013Available online 16 November 2013


    In this study, the impact ofindicators on rm value (ch19972011 was investigatednetworks.We divided the timthe robustness of results preas the predictors of rm va

    j ourna l homepage: wwwthe characteristics that.

    1 918 594 (A. Uyar),

    ghts reserved.: A comparative analysis of

    ma State University, United States

    tinationality (as measured by foreign sales ratio) and fourteen other nancialcterized by market capitalization and market-to-book ratio) for the period ofng two popular machine learning techniques: decision trees and articial neuraleriod of 19972011 into two periods; 19972004 and 20052011 to investigatend post-IFRS implementation. To determine the relative importance of factorsrst, a number of classication models are developed; then, the information

    ort Systems

    l sev ie r .com/ locate /dssin the emerging market context. Moreover, the present paper also dif-ferentiates itself from previous studies in the literature wherein theyutilized data mining and/or text mining in nancial reporting areafocusing primarily on detection of nancial statement fraud [9397].However, this study analyzes the impact of multinationality on rmvalue by using data mining technique and a broad set of nancial data.

  • In prior work, regression analysis has been frequently and primarilyused tools to investigate the association of internationalization with

    internationalization and the market value of the rm. Fauver et al. [35]

    128 C. Kuzey et al. / Decision Support Systems 59 (2014) 127142empirically proved that corporate international diversication isvalue reducing for U.S.rms on average, but has no signicant valuationinuence for German or U.K. rms. Schmid and Walter [82] used thepercentage of sales from non-domestic operations to measure the im-pact of geographic diversication, and they indicated that geographicdiversication is not associated with a signicant valuation discount innancial intermediaries.

    Machine learning (ML) as well as articial intelligence methodolo-gies have been used extensively to handle nancial decision makingproblems [5,6,19,21,37,74]. Furthermore, it has been proven that MLalgorithms such as support vector machines (SVM) demonstratedincreasingly important performances in nancial time series analysis[48,68].

    1 Beginning from 2005, Turkish listed companies have been required to adopt IFRS byrm value [31,35,58,82]. This study utilizes advanced analysis tech-niques of decision trees and articial neural networks. The data sampleused in this study includes Turkish non-nancial rms over the periodof 19972011. Within this time period, Turkish rms are mandated toadopt International Financial Reporting Standards (IFRS). Therefore,we conduct the analysis for the sub-periods of 19972004 and 20052011; doing so, we aim to examine whether the adoption of IFRS hasany impacted on the rm value characteristics.1

    The remainder of the paper is organized as follows. Next sectionprovides the literature review and makes the case for novelty andimportance of this study. Section 3 presents the methodology used forthe study; Section 4 documents the ndings of the study. Finally,Section 5 concludes the paper and explains the implications of the study.

    2. Literature review

    The information of whether multinationality affects rm value is animportant piece of information for decisionmakers for a number of rea-sons. Firstly, this information provides managers with guidance in rela-tion to whether and in which way to expand operations of the businessbeyond the borders of their own home country [31]. Secondly, presentor potential investors of a rm also want to knowwhich characteristicsare value-relevant so as to determine the direction of their investments.Finally, nancial analysts also wonder which factors impact rm valueso that they can make the best investment decision on behalf of theircustomers.

    Fauver et al. [35] state the motivations behind increase in foreigninvestment as improved communications, lower transaction costs, andincreasingly integrated foreign markets. However, they also argue thatmany rms incur additional costs and risks such as exchange rate, polit-ical instability, the agency costs, and coordination costs. Thus, the keyquestion to be answered is whether the internationalization reducesor increases rm value. In this context, more evidences are needed,since the existing evidence regarding the benets of internationaldiversication has yielded inconclusive results [35].

    Some of the previous studies have dealt with the relationshipbetween multinationality and rm value; however, their ndingswere inconsistent. For example, Eckert et al. [31] conducted theirstudy on German rms and concluded that multinationality is not avalue itself, but through either having intangible assets or realizingeconomies of scale. Eckert et al. [31] proved that leverage and sizehave a signicant negative impact on shareholder value, whereasprotability and capital intensity (as a proxy for economies of scaleand as measured by capital expenditures per sales) exert a signicantpositive effect. Riahi-Belkaoui [78] conducted a study on U.S. rms andconrmed that there is a positive relation between the degree ofthe Capital Markets Board.ML is the subeld of articial intelligence concerned with develop-ment of algorithms that allow computer programs to learn from experi-ence [56]. These algorithms are used in a variety of applications.ML algorithms are appropriate in scenarios where the applications in-volve large databases, making it difcult to establish models [66],where nancial data sets are large, as in our case. Various studies haveshown that machine learning techniques such as neural networks anddecision tree algorithms can be employed as an alternative method toresolve classication problems instead of the traditional statisticalmethods [6,9,10,14,19]. Traditional statistical methods use restrictiveassumptions such as normality, linearity, and independence amongpredictor variables. Deakin [26] demonstrated that violations of theseimportant assumptions of independent variables frequently happen innancial data. As a result, these conventional statistical methodsmight produce limitations in terms of validity and effectiveness. Deci-sion trees (DT) algorithms and neural networks (NN) are among themost popular machine learning algorithms. Several of these algorithmssuch as decision trees algorithms, support vector machines (SVM), neu-ral networkswere developed for application in nancial and accountingapplications [43,53,66,76]. Therefore, ML algorithms are the mostappropriate for this study.

    ML algorithms were employed successfully in some studies thatfocus on rm value. Chaehwan et al. [18] studied dividend policy fore-casting usingML approaches discovering that comparingML algorithmswas one of the most important managerial decisions affecting theprediction of rm value. Also, Chih-Fong et al. [22] used popular ML al-gorithms such as decision trees, genetic algorithms andneural networksto determine the most important features impacting rm value.

    In this study, machine learning (ML) techniques were applied as thedata driven approach. While various studies compare the machinelearning algorithms in general [98101] such as SVMs, neural nets, lo-gistic regression, naive bayes, memory-based learning, random forests,decision trees, bagged trees, and boosted trees, the comparison ofmachine learning algorithms versus classical statistical techniques wasstudied as well. A literature driven argument for the use of MLtechniques in this context, and a comparative analysis of traditional sta-tistical methods versus ML are summarized in Table 1. According toBreiman [102], statistics really starts with data and the main goals ofit: prediction (estimation) and information (detection). Breiman [102]claimed that higher predictive accuracy is associated withmore reliableinformation about the underlying data mechanism, therefore weakpredictive accuracy can lead to questionable conclusions. Moreover,he valued the importance of algorithmicmodels since they can give bet-ter predictive accuracy than data models, and therefore provide betterinformation about the underlying mechanism. In the light of Breiman's[102] valuable study, the ultimate goal in this study is to obtain accurateinformation.

    3. Theoretical background

    Four theories are proposed to explain the links betweenmultinationality and rm value: the internalization theory [67]; imper-fect world capital markets [33,67]; managerial objectives [67]; and taxavoidance and low-cost inputs [33,67]. According to the rst theory, in-ternalization theory, whichwas developed initially by Caves [17], a rmcan enhance its value by internalizing markets for its intangible assets(i.e. superior production skills, managerial skills, marketing abilities,patents, or consumer goodwill). According to this view, internalizationbrings buyers and sellers of information-based assets together [30],and rms can thenmaximize their revenues through selling or licensingtheir assets to rms in other countries [71]. The second theory regardingthe imperfection of world capital marketsmight prevent investors fromoptimally diversifying their portfolios internationally; therefore multi-national rms provide shareholders with an opportunity to diversifytheir investments [67,71]. The third theory, managerial objectives, also

    plays an important role in the internationalization decision, eventually

  • DItineU

    . Astineso

    lPauoisTad[1Appropriate analytical methods are needed to be developed sincemany databases do notlead to the classic forms of statistical data organizations (e.g., data from internet) [105].


    129C. Kuzey et al. / Decision Support Systems 59 (2014) 127142impactingrmvalue.Morck and Yeung [67] argue that internationaliza-tion might leave more room for managers to act in their own interests,

    Table 1Comparison of econometric theory based and data driven approaches.

    Econometric theory based approaches

    It is the traditional eld that deals with the quantication, collection, analysis,interpretation, and drawing conclusions from data [103].

    Assumes that the data are generated by a given stochastic data model [102].The statistical community has been committed to the almost exclusive use of datamodelsThis commitment has led to irrelevant theory, questionable conclusions, and has keptstatisticians from working on a large range of interesting current problems [102].

    Hypothesis testing in order to determine the causes and effects as well as modelinterpretation is critical. Goodness-of-Fit and parameter signicance are used formodeselection. [102]. It traditionally concerns itself with analyzing primary data that hasbeen collected to check specic research hypothesis; data can be of an experimentalnature [105].

    The sampling of a massive database cannot be analyzed with the traditional statisticalsampling theory tools [105]. The size of the dat...


View more >