The healthy operation of the stock market relies on sound liquidity. We utilize the semantic information from disclosure texts of listed companies on the China Science and Technology Innovation Board (STAR Market) to construct a daily corporate network. Through empirical tests and performance analyses of machine learning models, we elucidate the relationship between the similarity of company disclosure text contents and the temporal and spatial correlations of stock liquidity. Our liquidity indicators encompass trading costs, market depth, trading speed, and price impact, recognized across four dimensions. Furthermore, we reveal that the information loss caused by employing Minimum Spanning Tree (MST) topology significantly affects the explanatory power of network topology indicators for stock liquidity, with a more pronounced impact observed at the document level. Subsequently, by establishing a neural network model to predict next-day liquidity indicators, we demonstrate the temporal relationship of stock liquidity. We model a liquidity predicting task and train a daily liquidity prediction model incorporating Graph Convolutional Network (GCN) modules to solve it. Compared to models with the same parameter structure containing only fully connected layers, the GCN prediction model, which leverages company network structure information, exhibits stronger performance and faster convergence. We provide new insights for research on company disclosure and capital market liquidity.

Informal institutions can play a crucial role in fostering corporate and policy innovation, especially when formal institutions are weak. However, their intangible nature makes them difficult to quantify. In this paper, we proxy the strength of kinship-based informal institutions using surname homogeneity among business owners, specifically, the extent to which they share a limited number of surnames within the same county. Our analysis reveals that a one-standard-deviation increase in the strength of informal institutions leads to a 21.1% increase in patent filings and an 18.9% increase in policy innovation. We find that kinship-related informal institutions foster corporate innovation by compensating for weak formal institutions, enhancing protection for intellectual property rights, facilitating access to finance, improving public service delivery, and promoting supply chain cooperation. We also suggest that kinship-related informal institutions encourage local governments to engage in policy experimentation, which relies on the collaboration of business owners. This experimentation process is easier to coordinate and monitor in counties dominated by a few kinship networks. Both informal institutions and policy innovation contribute to economic development and foster entrepreneurial market entries. However, the positive impact of informal institutions declines over time as formal institutions strengthen in China.

The stock price of a firm is dynamically influenced by its own factors as well as those of its peers. In this study, we introduce a Graph Attention Network (GAT) integrated with WaveNet architecture—termed the GAT-WaveNet model—to capture both time-series and spatial dependencies for forecasting the stock price crash risk of Chinese listed firms from 2012 to 2021. Utilizing node-rolling techniques to prevent overfitting, our results show that the GAT-WaveNet model significantly outperforms traditional machine learning models in prediction accuracy. Moreover, investment portfolios leveraging the GAT-WaveNet model substantially exceed the cumulative returns of those based on other models.

Based on the sample of Chinese A-listed firms from 2003 to 2020, this paper investigates the effect of common institutional ownership on labor income share. The result shows that common institutional ownership can significantly increase firms’ labor income share. Mechanism tests indicate that common ownership can: 1) alleviate financial constraints by reducing the debt financing costs and increasing the trade credit financing, thus increasing the labor income share; 2) improve corporate innovation and therefore enhances the demand for highly-skilled labor, which eventually boost labor income share. Competitive hypothesis test represents that common institutional ownership can reduce the monopoly power of enterprises and decrease monopoly rent, so as to increase the proportion of labor in the distribution. Further analyses present that the network formed by the common ownership can effectively exert the financing support role of SOEs and the knowledge spillover effect of innovative-advantage firms, which contributes to the labor income share increasing of other related firms in the network connection. This study not only enriches the economic consequences of common institutional ownership, but also provides policy guidance for the government to further optimize the income-distribution pattern by deepening the reform of the financial market.

Using unique account-level data from a leading Chinese fintech platform, we investigate how financial influencers, the key information intermediaries in social finance, attract followers through a process of social transmission bias. We document a robust performance-following pattern wherein retail investors overextrapolate influencers’ past returns rather than rational learning in the social network from their past performance. The transmission bias is amplified by two mechanisms: (1) influencers’ active social engagement and (2) their index fund-heavy portfolios. Evidence further reveals influencers’self-enhancing reporting through selective performance disclosure. Crucially, the dynamics ultimately increase risk exposure and impair returns for follower investors.

We construct a novel risk-based similarity peer network by applying machine learning techniques to extract a comprehensive set of disclosed risk factors from firms' annual reports. We find that a firm's future returns can be significantly predicted by the past returns of its risk-similar peers, even after excluding firms within the same industry. A long-short portfolio, formed based on the returns of these risk-similar peers, generates an alpha of 84 basis points per month. This return predictability is particularly pronounced for negative-return stocks and those with limited investor attention, suggesting that the effect is driven by slow information diffusion across firms with similar risk exposures. Our findings highlight that the risk factors disclosed in 10-K filings contain valuable information that is often overlooked by investors.

We (re)evaluate the general-equilibrium effects of (environmental) policies from the perspectives of input-output networks and firm dynamics and heterogeneity. Using China’s carbon emission trading system (ETS) as an example, we find that ETS leads to more patent applications, especially the ones associated with low-carbon technologies in the targeted sectors. The effects are muted at the firm level due to selection effects, whereby only larger firms are significantly and positively affected. Meanwhile, larger firms occupy a small share in number but a large share of aggregate outcomes, contributing to the discrepancy between the effects of ETS at the individual firm and aggregate sector levels. The effects also diffuse in input-output networks, leading to more patents in upstream/downstream sectors. We build and estimate the first firm dynamics model with input-output linkages and regulatory policies in the literature and conduct policy experiments. ETS’s effects are amplified given input-output networks.

Utilizing a dataset from 2013 to 2022 on China’s listed companies, we explored whether a hedge fund network could help explain the occurrence of Chinese stock crash. First, this study constructs a hedge fund network based on common holdings. Then, from the perspective of network centrality, we examine the effect of hedge fund network on stock crash risk and its mechanism. Our findings show that companies with greater network centrality experience lower stock crash risk. Such results remain valid after alternating measures, using the propensity score matching method, and excluding other network effects. We further document that the centrality of hedge fund network reduces crash risk through three channels: information asymmetry, stock price information content and information delay. In addition, the negative effect of hedge fund network centrality on crash risk is more prominent for non-SOEs firms. In summary, our research shed light on the important role of hedge fund information network in curbing stock crash.

We conceptually identify and empirically verify the features distinguishing FinTech platforms from non-financial platforms using marketplace lending data. Specifically, we highlight three key features: (i) Long-term contracts introducing default risk at both the individual and platform levels; (ii) Lenders’ investment diversification to mitigate individual default risk; (iii) Platform-level default risk leading to greater asymmetric user stickiness and rendering platform-level cross-side network effects (p-CNEs), a novel metric we introduce, crucial for adoption and market dynamics. We incorporate these features into a model of two-sided FinTech platform with potential failures and endogenous participation and fee structures. Our model predicts lenders’ single-homing, occasional lower fees for borrowers, asymmetric p-CNEs, and the predictive power of lenders’ p-CNEs in forecasting platform failures. Empirical evidence from China’s marketplace lending industry, characterized by frequent market entries, exits, and strong network externalities, corroborates our theoretical predictions. We find that lenders’ p-CNEs are systematically lower on declining or well-established platforms compared to those on emerging or rapidly growing platforms. Furthermore, lenders’ p-CNEs serve as an early indicator of platform survival likelihood, even at the initial stages of market development. Our findings provide novel economic insights into the functioning of multi-sided FinTech platforms, offering valuable implications for both industry practitioners and financial regulators.

This study reconsiders the timing of the equity risk factors by using the flexible neural networks specified for image recognition to determine the timing weights. The performance of each factor is visualized to be standardized price and volatility charts and `learned' by flexible image recognition methods with timing weights as outputs. The performance of all groups of factors can be significantly improved by using these ``deep learning--based'' timing weights. In addition, visualizing the volatility of factors and using deep learning methods to predict volatility can significantly improve the performance of the volatility-managed portfolio for most categories of factors. Our further investigation reveals that the timing success of our method hinges on its ability in identifying ex ante regime switches such as jumps and crashes of the factors and its predictability on future macroeconomic risk.