Daejin Kim

Using data from South Korean public firms, we investigate the relationship between employee stock ownership (ESO) and stock price crash risk. We find that firms with higher ESO levels are associated with lower stock price crash risk. Moreover, employee ownership is related to less managerial bad‐news hoarding behaviour and greater transparency in corporate governance. This negative association is particularly more pronounced when the largest shareholder's ownership is low or when analyst coverage is high. We further demonstrate that ESO is associated with higher financial reporting quality and greater employee bargaining power in salary negotiations.

We study the effectiveness of textual information in predicting the returns of crude oil futures and understanding the behavior of market participants. Using a machine learning method to extract oil market sentiment from news articles, we find that the computed sentiment is significantly effective in explaining the crude oil futures returns, while existing textual analyses based on pre-defined dictionaries may mislead the contexts in the oil market. Consistent with previous findings that returns help explain the change in traders’ positions, the sentiment scores based on the machine learning method are also useful in explaining the behavior of different types of traders. Our empirical findings underscore the fact that accurately identifying textual information can increase the accuracy of oil price predictions and explain divergent behaviors of oil traders.

We apply the regression‐based affine term structure model to estimate the term structure of commodity futures. This model is advantageous in that it has a simple and fast algorithm, can accommodate a variety of observable and unspanned factors, and can be applied to daily and even real‐time observations. The results show that the model appropriately captures time‐series variations across different maturities and exhibits satisfactory performance in capturing cross‐sectional variations for specific months. Furthermore, we investigate the relationship between the existing commodity risk factor returns and the risk premiums inferred by the model. Our analysis reveals that different risk factor returns explain the spot and term premiums differently. Therefore, using the advantages of the model, we can better understand the term structure and risk premiums in commodity futures.

Purpose: To overcome the shortcomings of traditional industry classification systems such as the Standard Industrial Classification Standard Industrial Classification, North American Industry Classification System North American Industry Classification System, and Global Industry Classification Standard Global Industry Classification Standard, the authors explore industry classifications using machine learning methods as an application of interpretable artificial intelligence (AI).Design/methodology/approach: The authors propose a text-based industry classification combined with a machine learning technique by extracting distinguishable features from business descriptions in financial reports. The proposed method can reduce the dimensions of word vectors to avoid the curse of dimensionality when measuring the similarities of firms.Findings: Using the proposed method, the sample firms form clusters of distinctive industries, thus overcoming the limitations of existing classifications. The method also clarifies industry boundaries based on lower-dimensional information. The graphical closeness between industries can reflect the industry-level relationship as well as the closeness between individual firms.Originality/value: The authors’ work contributes to the industry classification literature by empirically investigating the effectiveness of machine learning methods. The text mining method resolves issues concerning the timeliness of traditional industry classifications by capturing new information in annual reports. In addition, the authors’ approach can solve the computing concerns of high dimensionality.