Announcement Premium Effect and Asset Pricing:A Textual Machine Learning Perspective
In recent years,the application of machine learning techniques within the financial market has become increasingly prevalent,underscoring the significant potential of these methods in accurately forecasting and explaining the market returns.Concurrently,big data is revolutionizing the finance industry and has the potential to significantly shape future research in finance.Goldstein et al.(2021)noted that new research built on these big data to push the frontier on fundamental issues across areas in finance.Textual data,with its large size,high dimensionality,and complex structure,epitomizes big data features.Corporate announcements are particularly noteworthy within this domain due to their high-quality information,which not only reveals a company's operational and development status but also communicates critical information that can significantly affect stock price.Consequently,it is valuable to mine effective pricing information from these corporate announcements to examine its predictive impact on returns.This paper analyzes textual data from corporate announcements spanning from 2000 to 2020.Through textual analysis,this paper constructs the sentiment dictionaries based on these announcements and employs machine learning techniques to assess the sentiment orientation(positive or negative)of each announcement,so as to investigate the influence of announcement content on the anticipated asset returns.Furthermore,this paper undertakes robustness tests and heterogeneity analyses of the announcement premium effect,offering an in-depth examination of the market's reaction mechanisms to this effect from multiple dimensions.The findings of this paper reveal several key insights.Firstly,there is a significant variance in the returns of stocks based on the category of announcements,with positive news yielding higher returns and negative news leading to lower returns.Secondly,the sentiment dictionary developed in this paper effectively differentiates the direction of stock returns,demonstrating a significantly positive announcement premium effect.Thirdly,in the heterogeneity analysis,the announcement premium effect is notably pronounced in small-scale,growth-oriented firms;compared with state-owned enterprises(SOEs),portfolios based on announcements in private firms exhibit higher returns.Additionally,the paper uncovers that the underlying cause of the announcement premium effect is the excessive attention from retail investors.For companies that are more closely monitored by financial institutions and have higher quality of information disclosure,the announcement premium effect is relatively weaker.The main contributions of this paper are as follows.Firstly,it offers a novel perspective on analyzing the effects of corporate announcements.Distinct from the conventional event study methods that focus on specific types of announcements,this paper employs textual analysis to extract information from all types of announcements,examining their effects from perspectives of information value and asset pricing.Secondly,this paper broadens the object of Chinese financial text analysis.In constructing the sentiment dictionary for announcements,this paper innovatively incorporates stock returns as weights to calculate the sentiment orientation of words in a supervised manner.This approach strengthens the link between the dictionary and stock returns,making it more relevant for research in asset pricing.Thirdly,this paper opens new avenues for quantitative investment strategies.By harnessing the power of machine learning to extract pricing information from corporate announcements,this method not only enhances the precision of investment analyses but also contributes to the optimization of investment portfolios based on data-driven evidence.Furthermore,the findings of this paper offer valuable insights for both corporate disclosure policies and regulatory frameworks.It underscores the importance for listed companies to prioritize the quality and accuracy of disclosed information.Regulatory bodies should enhance their oversight and guidance on corporate disclosure practices,promptly addressing inappropriate behaviors to safeguard investor interests and foster the healthy development of the capital market.
NETL
NSTL
万方数据
维普
