A generative model for the collective attention of the Chinese stock market investors

Collective attention of investors maps the interests and intention of investors directly in the stock market. However, the evolution mechanism of the collective attention from the viewpoint of complex system is missing. In this paper, we empirically investigate the investor collective attention mechanism based on a best-known stock trading platform between 2014 and 2016. Taking the global and recent popularity effects into account, we introduce a generative model for the collective attention of millions of investors who are deciding their trading behavior among thousands of stocks in Chinese stock market. The experimental results show that the investor attention is more closely affected by recent attention, with the optimal case, when the memory effect parameter T = 10 and the recent popularity parameter gamma = 0.1, the model could regenerate the collective attention more accurately, say Kendall's tau = 0.92 for the Shanghai Stock Exchange(SSE) and Shenzhen Stock Exchange(SZSE) simultaneously. This work may shed some lights for deeply understanding the mechanism of the investor collective attention for the financial market. (C) 2018 Elsevier B.V. All rights reserved.