nep-mst New Economics Papers
on Market Microstructure
Issue of 2021‒10‒18
five papers chosen by
Thanos Verousis

  1. General Compound Hawkes Processes for Mid-Price Prediction By Myles Sjogren; Timothy DeLise
  2. When is the Order to Trade fee effective? By Nidhi Aggarwal; Venkatesh Panchapagesan; Susan Thomas
  3. Ordinal Synchronization and Typical States in High-Frequency Digital Markets By Mario L\'opez P\'erez; Ricardo Mansilla
  4. Protecting Retail Investors from Order Book Spoofing using a GRU-based Detection Model By Jean-No\"el Tuccella; Philip Nadler; Ovidiu \c{S}erban
  5. Towards Robust Representation of Limit Orders Books for Deep Learning Models By Yufei Wu; Mahmoud Mahfouz; Daniele Magazzeni; Manuela Veloso

  1. By: Myles Sjogren (University of Calgary); Timothy DeLise (Universit\'e de Montr\'eal)
    Abstract: High frequency financial data is burdened by a level of randomness that is unavoidable and obfuscates the task of modelling. This idea is reflected in the intraday evolution of limit orders book data for many financial assets and suggests several justifications for the use of stochastic models. For instance, the arbitrary distribution of inter arrival times and the subsequent dependence structure between consecutive book events. This has lead to the development of many stochastic models for the dynamics of limit order books. In this paper we look to examine the adaptability of one family of such models, the General Compound Hawkes Process (GCHP) models, to new data and new tasks. We further focus on the prediction problem for the mid-price within a limit order book and the practical applications of these stochastic models, which is the main contribution of this paper. To this end we examine the use of the GCHP for predicting the direction and volatility of futures and stock data and discuss possible extensions of the model to help improve its predictive capabilities.
    Date: 2021–10
  2. By: Nidhi Aggarwal (Indian Institute of Management, Udaipur); Venkatesh Panchapagesan (Indian Institute of Management, Bangalore); Susan Thomas (xKDR Forum)
    Abstract: Regulators use measures such as a fee on high order to trade ratio (OTR) to slow down high frequency trading. Their impact on market quality is, however, mixed. We study a natural experiment in the Indian stock market where such a fee was introduced twice, with differences in motivation and implementation. Using a difference-in-difference approach, we find that the fee decreased OTR and improved market quality when it was imposed on all orders, while it had little effect when it was imposed selectively on some orders. Improvement in liquidity was driven by a reduction in adverse selection costs following lower OTR.
    JEL: G14 G18
    Date: 2021–10
  3. By: Mario L\'opez P\'erez; Ricardo Mansilla
    Abstract: In this paper we show, through the study of ordinal patterns, information theoretic and network measures and clustering algorithms, the presence of typical states in automated high-frequency records during a one-year period in the US stock market, characterized by their degree of centralized or descentralized synchronicity. We also find two whole coherent seasons of highly centralized and descentralized synchronicity, respectively.
    Date: 2021–10
  4. By: Jean-No\"el Tuccella; Philip Nadler; Ovidiu \c{S}erban
    Abstract: Market manipulation is tackled through regulation in traditional markets because of its detrimental effect on market efficiency and many participating financial actors. The recent increase of private retail investors due to new low-fee platforms and new asset classes such as decentralised digital currencies has increased the number of vulnerable actors due to lack of institutional sophistication and strong regulation. This paper proposes a method to detect illicit activity and inform investors on spoofing attempts, a well-known market manipulation technique. Our framework is based on a highly extendable Gated Recurrent Unit (GRU) model and allows the inclusion of market variables that can explain spoofing and potentially other illicit activities. The model is tested on granular order book data, in one of the most unregulated markets prone to spoofing with a large number of non-institutional traders. The results show that the model is performing well in an early detection context, allowing the identification of spoofing attempts soon enough to allow investors to react. This is the first step to a fully comprehensive model that will protect investors in various unregulated trading environments and regulators to identify illicit activity.
    Date: 2021–10
  5. By: Yufei Wu; Mahmoud Mahfouz; Daniele Magazzeni; Manuela Veloso
    Abstract: The success of machine learning models is highly reliant on the quality and robustness of representations. The lack of attention on the robustness of representations may boost risks when using data-driven machine learning models for trading in the financial markets. In this paper, we focus on representations of the limit order book (LOB) data and discuss the opportunities and challenges of representing such data in an effective and robust manner. We analyse the issues associated with the commonly-used LOB representation for machine learning models from both theoretical and experimental perspectives. Based on this, we propose new LOB representation schemes to improve the performance and robustness of machine learning models and present a guideline for future research in this area.
    Date: 2021–10

This nep-mst issue is ©2021 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.