nep-mst New Economics Papers
on Market Microstructure
Issue of 2021‒11‒22
four papers chosen by
Thanos Verousis
University of Essex

  1. Heterogenous criticality in high frequency finance: a phase transition in flash crashes By Jeremy Turiel; Tomaso Aste
  2. Ask "Who", Not "What": Bitcoin Volatility Forecasting with Twitter Data By M. Eren Akbiyik; Mert Erkul; Killian Kaempf; Vaiva Vasiliauskaite; Nino Antulov-Fantulin
  3. Trading via Selective Classification By Nestoras Chalkidis; Rahul Savani
  4. Costly Trading By Michael Isichenko

  1. By: Jeremy Turiel; Tomaso Aste
    Abstract: Flash crashes in financial markets have become increasingly important attracting attention from financial regulators, market makers as well as from the media and the broader audience. Systemic risk and propagation of shocks in financial markets is also a topic or great relevance who has attracted increasing attention in recent years. In the present work we bridge the gap between these two topics with an in-depth investigation of the systemic risk structure of co-crashes in high frequency trading. We find that large co-crashes are systemic in their nature and differ from small crashes. We demonstrate that there is a phase transition between co-crashes of small and large sizes, where the former involves mostly illiquid stocks while large and liquid stocks are the most represented and central in the latter. This suggest that systemic effects and shock propagation might be triggered by simultaneous withdrawn or movement of liquidity by HFTs and market makers having cross-asset.
    Date: 2021–10
  2. By: M. Eren Akbiyik; Mert Erkul; Killian Kaempf; Vaiva Vasiliauskaite; Nino Antulov-Fantulin
    Abstract: Understanding the variations in trading price (volatility), and its response to external information is a well-studied topic in finance. In this study, we focus on volatility predictions for a relatively new asset class of cryptocurrencies (in particular, Bitcoin) using deep learning representations of public social media data from Twitter. For the field work, we extracted semantic information and user interaction statistics from over 30 million Bitcoin-related tweets, in conjunction with 15-minute intraday price data over a 144-day horizon. Using this data, we built several deep learning architectures that utilized a combination of the gathered information. For all architectures, we conducted ablation studies to assess the influence of each component and feature set in our model. We found statistical evidences for the hypotheses that: (i) temporal convolutional networks perform significantly better than both autoregressive and other deep learning-based models in the literature, and (ii) the tweet author meta-information, even detached from the tweet itself, is a better predictor than the semantic content and tweet volume statistics.
    Date: 2021–10
  3. By: Nestoras Chalkidis; Rahul Savani
    Abstract: A binary classifier that tries to predict if the price of an asset will increase or decrease naturally gives rise to a trading strategy that follows the prediction and thus always has a position in the market. Selective classification extends a binary or many-class classifier to allow it to abstain from making a prediction for certain inputs, thereby allowing a trade-off between the accuracy of the resulting selective classifier against coverage of the input feature space. Selective classifiers give rise to trading strategies that do not take a trading position when the classifier abstains. We investigate the application of binary and ternary selective classification to trading strategy design. For ternary classification, in addition to classes for the price going up or down, we include a third class that corresponds to relatively small price moves in either direction, and gives the classifier another way to avoid making a directional prediction. We use a walk-forward train-validate-test approach to evaluate and compare binary and ternary, selective and non-selective classifiers across several different feature sets based on four classification approaches: logistic regression, random forests, feed-forward, and recurrent neural networks. We then turn these classifiers into trading strategies for which we perform backtests on commodity futures markets. Our empirical results demonstrate the potential of selective classification for trading.
    Date: 2021–10
  4. By: Michael Isichenko
    Abstract: We revisit optimal execution of an active portfolio in the presence of slippage (aka linear, proportional, or absolute-value) costs. Market efficiency implies a close balance between active alphas and trading costs, so even small changes to trading optimization can make a big difference. It has been observed for some time that optimal trading involves a pattern of a no-trade zone with width $\Delta$ increasing with slippage cost parameter $c$. In a setting of a reasonably stable (non-stochastic) forecast of future returns and a quadratic risk aversion, it is shown that $\Delta\sim c^{1/2}$, which differs from the $\Delta\sim c^{1/3}$ scaling reported for stochastic settings. Analysis of optimal trading employs maximization of a utility including projected alpha-based profits, slippage costs, and risk aversion and borrows from a physical analogy of forced motion in the presence of friction.
    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.