We examine whether corporate bankruptcy predictions can be improved by utilizing the recurrent neural network (RNN) and long short-term memory (LSTM) algorithms, which can process sequential data. ...Employing the RNN and LSTM methodologies improves bankruptcy prediction performance relative to using other classification techniques, such as logistic regression, support vector machine, and random forest methods. Because performance indicators, such as sensitivity and specificity, differ depending on the methodology, selecting a model that suits the purpose of the bankruptcy predictions is necessary. Our ensemble model, a synthesis of all methodologies, exhibits the best forecasting performance. In the test sample for the ensemble model, none of the observations with a default probability of less than 10% defaults within one year.
This study examines the market for green bonds, which have been in the spotlight as an eco-friendly investment product. We analyze the volatility dynamics and spillovers between the equity and green ...bond markets. As the return dynamics of financial products typically exhibit asymmetric volatility, we check whether green bonds also share this property. Our analyses confirm that although green bonds do exhibit the asymmetric volatility phenomenon, their volatility, unlike that of equity, is also sensitive to positive return shocks. An analysis of the association between the green bond and equity markets confirms that although the two markets have some volatility spillover effects, neither responds significantly to negative shocks in the other market.
This study investigates the relationships among information uncertainty, investor sentiment, analyst reports, and stock returns in a unified framework. The effects of analyst reports on stock returns ...depend on the degrees of information uncertainty, indicating that recommendation upgrades (downgrades) convey more valuable positive (negative) information under higher information uncertainty. Such stock market reactions are significantly explained by investor sentiment when information uncertainty is high. Our empirical findings are robust to changes in abnormal return measures and information uncertainty proxies.
•We examine the intermingled dynamics among information uncertainty, sentiment, analyst recommendations, and stock returns.•Analyst recommendations become less informative if information uncertainty is lower.•Sentiment explains the stock market reactions to analyst recommendation changes only under high information uncertainty.
This study shows that analysts generate firm-specific information, rather than market-wide information. Whereas previous studies report only the positive relationship between stock price ...synchronicity and analyst coverage, we suggest that the positive relation can be attributed to the interaction between analyst coverage and firm performance cyclicality. After controlling for the interaction effect between the analyst coverage and cyclicality, synchronicity decreases with the analyst coverage. Both effects diminish with the high analyst forecast dispersion, namely, we observe the decreasing effect of increasing analyst coverage on synchronicity and the increasing effect of interaction between analyst coverage and cyclicality.
•Analysts generate firm-specific information rather than market-wide information.•Firm performance cyclicality causes a positive relationship between stock price synchronicity and analyst coverage.•The effects of cyclicality and analyst coverage on synchronicity decrease with analyst forecast dispersion.
This study analyzes the relationship between the housing and stock markets, focusing on housing market bubbles. Stock market dynamics generally have a more significant impact on housing price ...movements than housing market dynamics have on stock dynamics. However, if housing market information is provided as a signal, housing price movements can predict stock market volatility. Accordingly, we build a machine learning-based early warning system (EWS) for the housing market using a long short-term memory (LSTM) neural network. Applying the generalized supremum augmented Dickey-Fuller test to extract the bubble signal in the housing market, we find that the signal simultaneously detects future changes in the housing market prices and future stock market volatility, and our EWS effectively detects the bubble signal. We confirm that the LSTM approach performs better than other benchmark models, the random forest and support vector machine models.
The strategic role of environmental, social, and governance (ESG) activities in firm performance has recently drawn increasing attention. In particular, the dynamics of ESG management in family-owned ...firms have become a crucial factor in increasing firm value. Using novel data from Korea, a suitable context for our analysis, we focus on the interplay between ESG investment and family ownership. Our results reveal that ESG activities can mitigate the agency problems inherent in family ownership, but their careful management is essential for maximizing firm value. We introduce the concept of the marginal effect of ESG, decompose its factors, and identify a critical threshold of family ownership that is instrumental for increasing firm value through ESG activities. Depending on a firm’s position relative to this threshold, we recommend strategies to increase or reduce ESG investment, showing that the timing of such investment or disinvestment in ESG activities emerges as a key strategic consideration. Our findings provide practical insights for family-owned firms to make informed decisions on ESG investment, thereby contributing not only to their own sustainability but also the long-term vitality of ESG activities.
As Korea's household debt has increased rapidly since the mid-2000s, concerns that its economy's hard-wired leveraging may negatively impact economic activity have grown. Calls are being made for ...policy actions to return the economy to its long-run trend. Housing preferences and monetary shocks can both trigger deleveraging, as most household debt is profoundly connected to the housing market, and debt growth increases sensitivity to interest rates. Constructing a dynamic stochastic general equilibrium model with heterogeneous households and the housing production sector, we simulate and analyze the macroeconomic effects of deleveraging. Because a lower loan-to-value (LTV) ceiling limits the size of household debt, the deleveraging effect caused by borrowers' re-optimization is alleviated as the LTV ceiling decreases. When the housing price is included as an additional operating target in an otherwise standard monetary policy (MP) rule, economy-wide welfare increases when the MP is proactive to demand shocks and inactive to supply shocks. These findings suggest that deleveraging risk can be attenuated by adopting a lower LTV ceiling and maneuvering MP asymmetrically depending on the source of a shock.
This study analyzes the impact of a newly emerging type of anti-money laundering regulation that obligates cryptocurrency exchanges to report suspicious transactions to financial authorities. We ...build a theoretical model for the reporting decision structure of a private bank or cryptocurrency exchange and show that an inferior ability to detect money laundering (ML) increases the ratio of reported transactions to unreported transactions. If a representative money launderer makes an optimal portfolio choice, then this ratio increases further. Our findings suggest that cryptocurrency exchanges will exhibit more excessive reporting behavior under this regulation than private banks. We attribute this result to cryptocurrency exchanges’ inferior ML detection abilities and their proximity to the underground economy.