nep-mst New Economics Papers
on Market Microstructure
Issue of 2019‒11‒11
two papers chosen by
Thanos Verousis

  1. Overnight Momentum, Informational Shocks, and Late-Informed Trading in China By Gao, Ya; Han, Xing; Li, Youwei; Xiong, Xiong
  2. Deep Learning for Stock Selection Based on High Frequency Price-Volume Data By Junming Yang; Yaoqi Li; Xuanyu Chen; Jiahang Cao; Kangkang Jiang

  1. By: Gao, Ya; Han, Xing; Li, Youwei; Xiong, Xiong
    Abstract: Based on high-frequency firm-level data, this paper uncovers new empirical patterns on intraday momentum in China. First, there exists a strong intraday momentum effect at the firm level. Second, the intraday predictability stems mainly from the overnight component rather than the opening half-hour component, which is consistent with the microstructure features of the Chinese market. Third, the intraday predictability attenuates (strengthens) following large positive (negative) informational shocks, implying a striking asymmetric reaction by market participants. Finally, we document that late-informed traders are relatively less experienced or skilful. Overall, the empirical results lend support to the model of late-informed trading.
    Keywords: intraday momentum; overnight return; price jump; late-informed trading
    JEL: G12 G14 G15 G17
    Date: 2019–09–16
  2. By: Junming Yang; Yaoqi Li; Xuanyu Chen; Jiahang Cao; Kangkang Jiang
    Abstract: Training a practical and effective model for stock selection has been a greatly concerned problem in the field of artificial intelligence. Even though some of the models from previous works have achieved good performance in the U.S. market by using low-frequency data and features, training a suitable model with high-frequency stock data is still a problem worth exploring. Based on the high-frequency price data of the past several days, we construct two separate models-Convolution Neural Network and Long Short-Term Memory-which can predict the expected return rate of stocks on the current day, and select the stocks with the highest expected yield at the opening to maximize the total return. In our CNN model, we propose improvements on the CNNpred model presented by E. Hoseinzade and S. Haratizadeh in their paper which deals with low-frequency features. Such improvements enable our CNN model to exploit the convolution layer's ability to extract high-level factors and avoid excessive loss of original information at the same time. Our LSTM model utilizes Recurrent Neural Network'advantages in handling time series data. Despite considerable transaction fees due to the daily changes of our stock position, annualized net rate of return is 62.27% for our CNN model, and 50.31% for our LSTM model.
    Date: 2019–11

This nep-mst issue is ©2019 by Thanos Verousis. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.