|
on Market Microstructure |
| By: | Zihao Zhang; Stefan Zohren; Stephen Roberts |
| Abstract: | We showcase how dropout variational inference can be applied to a large-scale deep learning model that predicts price movements from limit order books (LOBs), the canonical data source representing trading and pricing movements. We demonstrate that uncertainty information derived from posterior predictive distributions can be utilised for position sizing, avoiding unnecessary trades and improving profits. Further, we test our models by using millions of observations across several instruments and markets from the London Stock Exchange. Our results suggest that those Bayesian techniques not only deliver uncertainty information that can be used for trading but also improve predictive performance as stochastic regularisers. To the best of our knowledge, we are the first to apply Bayesian networks to LOBs. |
| Date: | 2018–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1811.10041&r=mst |
| By: | Brugler, James (University of Melbourne); Linton, Oliver (University of Cambridge); Noss, Joseph (Financial Stability Board); Pedace, Lucas (Bank of England) |
| Abstract: | This paper uses transaction data to estimate how single stock circuit breakers on the London Stock Exchange affect other stocks that remain in continuous trading. This ‘spillover’ effect is estimated by calculating the effect of a trading halt on the market quality of stocks that remain in continuous trading and comparing this with the effect of a stock whose absolute returns are of a magnitude nearly sufficient to trigger a trading halt but do not do so. Market quality is measured using a combination of trading costs, volatility and volume. We find that circuit breakers lead to a significant improvement in the liquidity, and reduction in the volatility, of stocks that remain in continuous trading. This might suggest that — at least over the period covered by our data — single stock circuit breakers play an important role in reducing the spillover of poor market quality across stocks. |
| Keywords: | Circuit breakers; market microstructure; market quality |
| JEL: | G12 G14 G15 G18 |
| Date: | 2018–10–12 |
| URL: | http://d.repec.org/n?u=RePEc:boe:boeewp:0759&r=mst |
| By: | Zhang, Shengxing |
| Abstract: | To understand the illiquidity of the over-the-counter market when dealers and traders are in long-term relationships, I develop a framework to study the endogenous liquidity distortions resulting from the profit-maximizing, screening behavior of dealers. The dealer offers the trading mechanism contingent on the aggregate history of his customers summarized by the asset allocation. The equilibrium distortion is type dependent: trade with small surplus breaks down; trade with intermediate surplus may be delayed; trade with large surplus is carried out with a large bid/ask spread but without delay. Because of dealers' limited commitment, the distortions become more severe when the valuation shock is frequent, the valuation dispersion is large or the matching friction to form new relationships is large. Calibrating the model and running a horse race between matching efficiency, trading speed and relationship stability, I found that the liquidity disruption in the market during the recent financial crisis is more consistent with declining matching efficiency of forming trading relationsh |
| Keywords: | screening; liquidity; long-term relationship; over-the-counter markets |
| JEL: | D82 D83 G1 |
| Date: | 2018–03–01 |
| URL: | http://d.repec.org/n?u=RePEc:ehl:lserod:86800&r=mst |
| By: | Vangelis Bacoyannis; Vacslav Glukhov; Tom Jin; Jonathan Kochems; Doo Re Song |
| Abstract: | We outline the idiosyncrasies of neural information processing and machine learning in quantitative finance. We also present some of the approaches we take towards solving the fundamental challenges we face. |
| Date: | 2018–11 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1811.09549&r=mst |
| By: | Nikolaus Hautsch; Christoph Scheuch; Stefan Voigt |
| Abstract: | Distributed ledger technologies rely on consensus protocols confronting traders with random waiting times until the transfer of ownership is accomplished. This time-consuming settlement process exposes arbitrageurs to price risk and imposes limits to arbitrage. We derive theoretical arbitrage boundaries under general assumptions and show that they increase with expected latency, latency uncertainty, spot volatility, and risk aversion. Using high-frequency data from the Bitcoin network, we estimate arbitrage boundaries due to settlement latency of on average 124 basis points, covering 88 percent of the observed cross-exchange price differences. Settlement through decentralized systems thus induces non-trivial frictions affecting market efficiency and price formation. |
| Date: | 2018–12 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:1812.00595&r=mst |