Corporate social responsibility in family business: Using machine learning to uncover who is doing good

Feng Liu, Wanying Huang, Jing Zhang and Mingjie Fang

Technology in Society, 2024, vol. 76, issue C

Abstract: Rapid social and environmental changes continue to highlight the critical role of corporate social responsibility (CSR) in business operations. Research on the determinants of CSR has received widespread attention. However, there has been little focus on family businesses, which play an important function in the economy and differ from non-family firms. Synthesizing the resource-based view (RBV) with the behavioral agency theory (BAT), this study aimed to examine the factors that drive the CSR performance of family businesses from the perspective of the firm and chief executive officer (CEO) characteristics. By comparing the performance of a set of machine learning (ML) techniques, we found that the best predictive model with the lowest mean squared error is the random forest algorithm. The results from the random forest indicated that profitability was the most important attribute of CSR performance, followed by firm size, CEO education, leverage, and board ownership. This study is one of the first to adopt an ML approach to investigate the drivers of CSR performance in family businesses. The novel findings provide a deeper understanding of how the various aspects of a family business firm affect its CSR performance, which can facilitate future research.

Keywords: Corporate social responsibility; Family business; Firm characteristics; CEO characteristics; Machine learning (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0160791X24000010
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:teinso:v:76:y:2024:i:c:s0160791x24000010

DOI: 10.1016/j.techsoc.2024.102453

Access Statistics for this article

Technology in Society is currently edited by Charla Griffy-Brown

More articles in Technology in Society from Elsevier
Bibliographic data for series maintained by Catherine Liu ().