Portfolio underdiversification is one of the most costly losses accumulated over a household’s life cycle. We provide new evidence on the impact of financial inclusion services on households’ portfolio choice and investment efficiency using 2015, 2017, and 2019 survey data for Chinese households. We hypothesize that higher financial inclusion penetration encourages households to participate in the financial market, leading to better portfolio diversification and investment efficiency. The results of the baseline model are consistent with our proposed hypothesis that higher accessibility to financial inclusion encourages households to invest in risky assets and increases investment efficiency. We further estimate a dynamic double machine learning model to quantitatively investigate the non-linear causal effects and track the dynamic change of those effects over time. We observe that the marginal effect increases over time, and those effects are more pronounced among low-asset, less-educated households and those located in non-rural areas, except for investment efficiency for high-asset households.

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.

We develop an information choice model where information costs are sticky and co-move with firm-level intrinsic uncertainty as opposed to temporal variations in uncertainty. Incorporating analysts' forecasts, we predict a negative relationship between information costs and information acquisition, as proxied by the predictability of analysts' forecast biases. Finally, the model shows a contrasting pattern between information acquisition and intrinsic and temporal uncertainty, where intrinsic uncertainty strengthens return predictability of analysts' biases through the information cost channel, while temporal uncertainty weakens it through the information benefit channel. We empirically confirm these opposing relationships that existing theories struggle to explain.

We construct a daily Chinese Housing Market Sentiment Index by applying GPT-4o to Chinese news articles. Our method outperforms traditional models in several validation tests, including a test based on a suite of machine learning models. Applying this index to household-level data, we find that after monetary easing, an important group of homebuyers (who have a college degree and are aged between 30 and 50) in cities with more optimistic housing sentiment have lower responses in non-housing consumption, whereas for homebuyers in other age-education groups, such a pattern does not exist. This suggests that current monetary easing might be more effective in boosting non-housing consumption than in the past for China due to weaker crowding-out effects from pessimistic housing sentiment. The paper also highlights the need for complementary structural reforms to enhance monetary policy transmission in China, a lesson relevant for other similar countries. Methodologically, it offers a tool for monitoring housing sentiment and lays out some principles for applying generative AI models, adaptable to other studies globally.

We propose a novel measure, DOT, to capture belief divergence on extreme tail events in stock returns. Defined as the standard deviation of expected probability forecasts generated by distinct information processing functions and neural network models, DOT exhibits significant predictive power for future stock returns. A value-weighted (equal-weighted) long-short portfolio based on DOT yields an average return of -1.07% (-0.98%) per month. Furthermore, we document novel evidence supporting a risk-sharing channel underlying the negative relation between DOT and the equity premium following extreme negative shocks. Finally, our findings are also in line with a mispricing channel in normal periods.

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.

This research study primarily examines the digital transformation’s internal mechanism promoting enterprises’ total factor productivity (TFP) based on the matching and learning mechanism. Afterward, this research article empirically examines the digital transformation’s influential mechanism on enterprises’ TFP, using the Chinese listed companies’ data on the “A” stock market for the time period ranging from 2007 to 2019. The major study findings are as follows: (1) the improvement of the digital transformation significantly increases enterprises’ TFP. The proposed conclusion remains robust after a series of robustness- and the endogeneity test. (2) Furthermore, mechanism analysis reveals that digital transformation effectively enhances enterprises’ TFP by eliminating resource misallocation in the industry. In addition to this, digital transformation relies on the mechanism of “learning by doing” to promote the technological innovation’s spillover effect; hence, effectively enhancing enterprises’ TFP. (3) Heterogeneity analysis demonstrates that the digital transformation’s impact on enterprises’ TFP is heterogeneous in the context of enterprise size, enterprise type, and enterprise ownership. Lastly, this study puts forward that government bodies should intensify the construction and investment in digital infrastructure, promote a series of institutional reforms, and support digital technological R&D practices.

This article applies natural language processing (NLP) to extract and quan- tify textual information to predict stock performance. Leveraging an exten- sive dataset of Chinese analyst reports and employing a customized BERT deep learning model for Chinese text, this study categorizes the sentiment of the reports as positive, neutral, or negative. The findings underscore the predictive capacity of this sentiment indicator for stock volatility, excess re- turns, and trading volume. Specifically, analyst reports with strong positive sentiment will increase excess return and intraday volatility, and vice versa, reports with strong negative sentiment also increase volatility and trading volume, but decrease future excess return. The magnitude of this effect is greater for positive sentiment reports than for negative sentiment reports. This article contributes to the empirical literature exploring sentiment anal- ysis and the response of the stock market to news on the Chinese stock market.

This paper employs a difference-in-differences approach to study whether a Chinese audit firm improves its competencies through organizational learning after one of its audit teams has a client cross-listed in the US. Among a group of companies that are listed only in China, we define those audited by firms that have cross-listed clients as the treatment group, and companies audited by other firms as the control group. We find an improvement in audit quality for the treatment group after their audit firms have cross-listed client experience in the US. A large-scale survey of auditors corroborates these findings and sheds light on specific actions undertaken by audit firms to facilitate learning. Both the empirical and survey results highlight the benefits of auditing crosslisted clients in the US and its positive externality on improving the audit quality of non-US-listed companies.

This study explores the intricate relationship between emotional cues present in food delivery app reviews, normative ratings, and reader engagement. Utilizing lexicon-based unsupervised machine learning, our aim is to identify eight distinct emotional states within user reviews sourced from the Google Play Store. Our primary goal is to understand how reviewer star ratings impact reader engagement, particularly through thumbs-up reactions. By analyzing the influence of emotional expressions in user-generated content on review scores and subsequent reader engagement, we seek to provide insights into their complex interplay. Our methodology employs advanced machine learning techniques to uncover subtle emotional nuances within user-generated content, offering novel insights into their relationship. The findings reveal an inverse correlation between review length and positive sentiment, emphasizing the importance of concise feedback. Additionally, the study highlights the differential impact of emotional tones on review scores and reader engagement metrics. Surprisingly, user-assigned ratings negatively affect reader engagement, suggesting potential disparities between perceived quality and reader preferences. In summary, this study pioneers the use of advanced machine learning techniques to unravel the complex relationship between emotional cues in customer evaluations, normative ratings, and subsequent reader engagement within the food delivery app context.