In finance, it is believed that market information, namely, fundamentals and news information, affects stock movements. Such media-aware stock movements essentially comprise a multimodal problem. Two unique challenges arise in processing these multimodal data. First, information from one data mode will interact with information from other data modes. A common strategy is to concatenate various data modes into one compound vector; however, this strategy ignores the interactions among different modes. The second challenge is the heterogeneity of the data in terms of sampling time. Specifically, fundamental data consist of continuous values sampled at fixed time intervals, whereas news information emerges randomly. This heterogeneity can cause valuable information to be partially missing or can distort the feature spaces. In addition, the study of media-aware stock movements in previous work has focused on the one-to-one problem, in which it is assumed that news affects only the performance of the stocks mentioned in the reports. However, news articles also impact related stocks and cause stock co-movements. In this article, we propose a tensor-based event-driven LSTM model to address these challenges. Experiments performed on the China securities market demonstrate the superiority of the proposed approach over state-of-the-art algorithms, including AZFinText, eMAQT, and TeSIA.

The low-carbon pilot city policy is an important initiative to explore the path of a win-win situation for both the economy and the environment. Since 2010, China has established 87 low-carbon pilot cities. This policy implementation aims to encourage green technology innovation among listed companies, thereby achieving sustainable corporate growth through the promotion of energy efficiency and renewable energy. This paper aims to unveil the relationship between low-carbon pilot city policies and green technology innovation. This paper explores the impact of policy implementation based on patent data of Chinese listed companies from 2007 to 2019. Empirical results show that the policy can promote green technology innovation among listed companies in the pilot cities. This finding still holds in the parallel trend test and the PSM-Multi-period DID test. Second, the policy has a greater effect on the green-technology innovation of non-state enterprises and can promote more green technology innovation activities of enterprises in the eastern region compared with other areas. Furthermore, in terms of different stock sectors, the low-carbon pilot city policy can significantly promote GEM-affiliated enterprises’ green technology innovation activities. Finally, listed companies with a high degree of digital transformation are more active in green technology innovation in the context of low-carbon pilot city policy.

The Stock Market is a typical complex network composed of investors, stocks, and market information. The abnormal fluctuation of the Stock Market has a strong effect on the economy of a country and even that of the world. Fueled by the herd effect of the increasingly abundant social media, Internet rumors, as an important source of market information and an exogenous financial risk, can lead to the collapse of investor confidence and the further propagation of financial risks, which can damage the financial system and even lead to social unrest. With additional availability of computing techniques, we attempt to uncover the media information effects in the stock market and seek to provide researchers with 1) a theoretical reference for a comprehensive understanding of such a complex network, 2) accurate prediction of future data, and 3) design of efficient and reliable risk intervention models. Based on the data of China’s Stock Market, this study uses machine learning to investigate social media rumors to reveal the interplay of social media rumors and stock market volatility. In this work, we find patterns from social media rumors from financial forums using machine learning, quantify social media rumors based on statistics, and analyze the mechanism of propagation and influence of social media rumors on stock market volatility using econometric models. The empirical results show that rumors play an important information transmission effect on stock market volatility and the constructed Internet Financial Forum Rumor Index is helpful to sense the potential impact of rumors, i.e., a significant lagged negative effect. These findings are of guidance for the optimization of the information environment, and can serve to promote the healthy and stable development of the stock market.

As an important part of financial market, stock market price volatility analysis has been the focus of academic and industry attention. Candlestick chart, as the most widely used indicator for evaluating stock market price volatility, has been intensively studied and explored. With the continuous development of computer technology, the stock market analysis method based on candlestick chart is gradually changed from manual to intelligent algorithm. However, how to effectively use stock market graphical indicators to analyze stock market price fluctuations has been pending solution, and deep learning algorithms based on structured data such as deep neural networks (DNN) and recurrent neural networks (RNNs) always have the problems of making it difficult to capture the laws and low generalization ability for stock market graphical indicators data processing. Therefore, this paper proposes a quantification method of stock market candlestick chart based on Hough variation, using the graph structure embedding method to represent candlestick chart features and multiple attention graph neural network for stock market price fluctuation prediction. The experimental results show that the proposed method can interpret the candlestick chart features more accurately and has superiority performance over state-of-the-art deep learning methods, including SVM, CNN, LSTM, and CNN-LSTM. Relative to these algorithms, the proposed method achieves an average performance improvement of 20.51% in terms of accuracy and further achieves at least 26.98% improvement in strategy returns in quantitative investment experiments.