|
on Market Microstructure |
| By: | Lorenzo Lucchese; Mikko Pakkanen; Almut Veraart |
| Abstract: | In this paper, we conduct a systematic large-scale analysis of order book-driven predictability in high-frequency returns by leveraging deep learning techniques. First, we introduce a new and robust representation of the order book, the volume representation. Next, we conduct an extensive empirical experiment to address various questions regarding predictability. We investigate if and how far ahead there is predictability, the importance of a robust data representation, the advantages of multi-horizon modeling, and the presence of universal trading patterns. We use model confidence sets, which provide a formalized statistical inference framework particularly well suited to answer these questions. Our findings show that at high frequencies predictability in mid-price returns is not just present, but ubiquitous. The performance of the deep learning models is strongly dependent on the choice of order book representation, and in this respect, the volume representation appears to have multiple practical advantages. |
| Date: | 2022–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2211.13777&r=mst |
| By: | Robert Czech (Bank of England); Gábor Pintér (Bank of England) |
| Abstract: | Using a unique non-anonymous UK dataset, we show that clients in corporate bond markets outperform when they trade with more dealers. The effect is stronger for informationally sensitive clients, assets, and during informationally intensive periods including COVID-19. Identifying clients who simultaneously trade in government and corporate bonds reveals that connections have a larger and more persistent effect in the corporate bond market. Using a Kyle (1989)-type model, we show that both the degree of inter-dealer competition and the magnitude of private information could explain the strength of the performance-connection relation; only the latter mechanism is supported by the data. |
| Keywords: | Informed Trading, Corporate Bonds, Client-Dealer Connections, Inter-Dealer Competition, COVID-19 |
| Date: | 2020–12 |
| URL: | http://d.repec.org/n?u=RePEc:cfm:wpaper:2032&r=mst |
| By: | Guglielmo Maria Caporale; Alex Plastun |
| Abstract: | This paper investigates persistence in high-frequency, intraday data (and also daily and monthly ones) in the case of the EuroStoxx 50 futures over the period from 2002 to 2018 (720 million trade records) using R/S analysis and the Hurst exponent as a measure of persistence. The results indicate that persistence is sensitive to the data frequency. More specifically, monthly data are highly persistent, daily ones follow a random walk, and intraday ones are anti-persistent. In addition, persistence varies over time. These findings imply that the Efficient Market Hypothesis (EMH) only holds in the case of daily data, whilst it is possible to make abnormal profits using trading strategies based on reversal strategies at the intraday frequency. |
| Keywords: | persistence, long memory, R/S analysis, high-frequency data |
| JEL: | C22 G12 |
| Date: | 2022 |
| URL: | http://d.repec.org/n?u=RePEc:ces:ceswps:_10045&r=mst |
| By: | Samuel M. Hartzmark; David H. Solomon |
| Abstract: | We demonstrate that predictable uninformed cash flows forecast market and individual stock returns. Buying pressure from dividend payments (announced weeks prior) predicts higher value-weighted market returns, with returns for the top quintile of payment days four times higher than the lowest. This holds internationally, and increases when reinvestment is high and market liquidity is low. High stock expense firms have lower returns from selling pressure after blackout periods, by 117 b.p. in four days. We estimate market-level price multipliers of 1.5 to 2.3. These results suggest price pressure is a widespread result of flows, not an anomaly. |
| JEL: | G12 G14 G4 |
| Date: | 2022–11 |
| URL: | http://d.repec.org/n?u=RePEc:nbr:nberwo:30688&r=mst |