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.

As carbon emission reduction is being emphasized globally, the importance of efficient building operations to reduce energy use is emerging as an important factor. To optimize building operations (i.e., achieving better facility conditions with less energy use), this research proposes a methodology that leverages 1) the DBSCAN algorithm to not only cluster groups but identify anomalous behaviors and 2) the DBA algorithm to have a representative case of each cluster group. The methodology is demonstrated against real-world operational data (e.g., time-series temperature) of Building A operated by the Mastern Investment Group located in Seoul, South Korea. As a result, the anomalous cases are identified by the methodology, leading to interviews with the facility managers. After the cause of anomalies is defined and reasoned through discussion with the managers, a couple of strategies are suggested to the managers with the aim of managing the building in an efficient manner.

With video marketing platforms growing rapidly, brands create YouTube channels to distribute their content and communicate with customers. This study proposes a prediction model analyzing 16,278 image data sets collected based on 153 brand channels generated before September 26, 2022. We analyze the factors affecting the number of image views of brand channels using the data set, and constructs a view prediction model. The study found that the characteristics of the thumbnail image, offline top brand characteristics, and the size of the channel (number of subscribers, number of channel videos) affect YouTube’s top online channel views. The results of the study make it possible to predict branded content before uploading it, and it can help the brand for planning content production and marketing activities through YouTube.

Music videos are one of the most important factors for stakeholders in the music industry.