This study examines the role of corporate governance in predicting firm’s CSR performance. In particular, we measure related-party transactions (RPTs), which can provide benefits as well as detrimental practices such as "tunneling", that infringe minority shareholder value. By applying machine learning techniques, the research investigates how corporate governance influence predicting market performance, as measured by the Price-to-Book Ratio (PBR), and Corporate Social Responsibility (CSR) performance. The results suggest that model including related-party transactions variables improve prediction performance on max average 10% compared to those using only financial variables, particularly with a noticeable improvement in lower 20% of PBR value companies. This emphasizes the importance of considering related-party transactions variables in corporate valuation and the value of taking a comprehensive approach to these variables in related research. The study offers practical implications for improving corporate governance and CSR, ultimately supporting investor decision-making.

The employee-generated online review data has emerged as a critical resource for disseminating internal company information to potential employees (i.e., job seekers), thereby reducing information asymmetry. This has enhanced the matching efficiency between companies and job seekers. We gathered employee review data from 1,041 companies from JobPlanet and JobKorea, job search platforms in South Korea. The dataset encompasses numerical scores reflecting employee satisfaction and overall corporate evaluation, along with company profiles detailing employee numbers, revenue, business type, industry, and salary data. This study focuses on analyzing the impact of online review data on the recruitment performance of companies.