nep-mst New Economics Papers
on Market Microstructure
Issue of 2022‒03‒07
five papers chosen by
Thanos Verousis

  1. Modeling bid and ask price dynamics with an extended Hawkes process and its empirical applications for high-frequency stock market data By Kyungsub Lee; Byoung Ki Seo
  2. DeepScalper: A Risk-Aware Deep Reinforcement Learning Framework for Intraday Trading with Micro-level Market Embedding By Shuo Sun; Rundong Wang; Xu He; Junlei Zhu; Jian Li; Bo An
  3. The Bright Side of Dark Markets: Experiments By Halim, Edward; Riyanto, Yohanes E.; Roy, Nilanjan; Wang, Yan
  4. Price Revelation from Insider Trading: Evidence from Hacked Earnings News By Akey, Pat; Grégoire, Vincent; Martineau, Charles
  5. Information-Based Trading By George Bouzianis; Lane P. Hughston; Leandro S\'anchez-Betancourt

  1. By: Kyungsub Lee; Byoung Ki Seo
    Abstract: This study proposes a versatile model for the dynamics of the best bid and ask prices using an extended Hawkes process. The model incorporates the zero intensities of the spread-narrowing processes at the minimum bid-ask spread, spread-dependent intensities, possible negative excitement, and nonnegative intensities. We apply the model to high-frequency best bid and ask price data from US stock markets. The empirical findings demonstrate a spread-narrowing tendency, excitations of the intensities caused by previous events, the impact of flash crashes, characteristic trends in fast trading over time, and the different features of market participants in the various exchanges.
    Date: 2022–01
  2. By: Shuo Sun; Rundong Wang; Xu He; Junlei Zhu; Jian Li; Bo An
    Abstract: Reinforcement learning (RL) techniques have shown great success in quantitative investment tasks, such as portfolio management and algorithmic trading. Especially, intraday trading is one of the most profitable and risky tasks because of the intraday behaviors of the financial market that reflect billions of rapidly fluctuating values. However, it is hard to apply existing RL methods to intraday trading due to the following three limitations: 1) overlooking micro-level market information (e.g., limit order book); 2) only focusing on local price fluctuation and failing to capture the overall trend of the whole trading day; 3) neglecting the impact of market risk. To tackle these limitations, we propose DeepScalper, a deep reinforcement learning framework for intraday trading. Specifically, we adopt an encoder-decoder architecture to learn robust market embedding incorporating both macro-level and micro-level market information. Moreover, a novel hindsight reward function is designed to provide the agent a long-term horizon for capturing the overall price trend. In addition, we propose a risk-aware auxiliary task by predicting future volatility, which helps the agent take market risk into consideration while maximizing profit. Finally, extensive experiments on two stock index futures and four treasury bond futures demonstrate that DeepScalper achieves significant improvement against many state-of-the-art approaches.
    Date: 2021–12
  3. By: Halim, Edward; Riyanto, Yohanes E.; Roy, Nilanjan; Wang, Yan
    Abstract: We design an experiment to study the effects of dark trading on incentives to acquire costly information, price efficiency, market liquidity, and investors' earnings in a financial market. When the information precision is high, adding a dark pool alongside a lit exchange encourages information acquisition, crowds out liquidity from the lit market, and results in a non-linear relationship between price efficiency and dark pool participation. At modest levels, dark pools enhance information aggregation. Investors with stronger signals use the lit exchange relatively more, and uninformed traders are better off when they trade more in the dark pool.
    Keywords: Market institutions, dark pools, information aggregation, the efficiency of security markets, costly information acquisition, experiments
    JEL: C91 C92 G12 G14
    Date: 2022–02–03
  4. By: Akey, Pat; Grégoire, Vincent (HEC Montréal); Martineau, Charles (University of Toronto)
    Abstract: From 2010 to 2015, a group of traders illegally accessed earnings information before their public release by hacking several newswire services. We use this scheme as a natural experiment to investigate how informed investors select among private signals and how efficiently financial markets incorporate private information contained in trades into prices. We construct a measure of qualitative information using machine learning and find that the hackers traded on both qualitative and quantitative signals. The hackers’ trading caused 15% more of the earnings news to be incorporated in prices before their public release. Liquidity providers responded to the hackers’ trades by widening spreads.
    Date: 2021–12–01
  5. By: George Bouzianis; Lane P. Hughston; Leandro S\'anchez-Betancourt
    Abstract: We consider a pair of traders in a market where the information available to the second trader is a strict subset of the information available to the first trader. The traders make prices based on the information available concerning a security that pays a random cash flow at a fixed time $T$ in the future. Market information is modelled in line with the scheme of Brody, Hughston & Macrina (2007, 2008) and Brody, Davis, Friedman & Hughston (2009). The risk-neutral distribution of the cash flow is known to the traders, who make prices with a fixed multiplicative bid-offer spread and report their prices to a game master who declares that a trade has been made when the bid price of one of the traders crosses the offer price of the other. We prove that the value of the first trader's position is strictly greater than that of the second. The results are analyzed by use of simulation studies and generalized to situations where (a) there is a hierarchy of traders, (b) there are multiple successive trades, and (c) there is inventory aversion.
    Date: 2022–01

This nep-mst issue is ©2022 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.