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 language | English |
|---|---|
| Pages (from-to) | 127-142 |
| Number of pages | 16 |
| Journal | Decision Support Systems |
| Volume | 59 |
| Issue number | 1 |
| DOIs | |
| State | Published - 1 Mar 2014 |
| Externally published | Yes |
Fingerprint
Keywords
- Artificial neural networks
- Decision trees
- Firm value
- Machine learning
- Multinationality
- Predictive analytics
- Sensitivity analysis
Cite this
}
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 journal › Article
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 -