The Quantitative Methods in Finance 2015 Conference (QMF2015) : 15-18 December, Sydney. Australia
QMF 2015 Program Abstracts
QuERI Lab contributed talks:
1. Detecting Temporal Financial Market States Using Clustering
Dieter Hendricks, University of the Witwatersrand, South Africa
ABSTRACT: We propose the application of a high‐speed maximum likelihood clustering algorithm to detect temporal states in the financial market, using estimated correlation matrices from intraday market microstructure features. We first determine the ex‐ante intraday temporal cluster configurations to identify financial states. Next, temporal state features are studied to extract characteristic feature vectors. The latter serve as low‐dimensional state descriptors which can be used efficiently in learning algorithms, enabling online state detection for optimal planning in the high‐frequency trading domain.
Authors: Dieter Hendricks, Tim Gebbie, Diane Wilcox
When: Wednesday, 16 December 2015, 14h20 Room 3
2. Reconciling Order Book Resiliency and Price Impact
Michael Harvey, University of the Witwatersrand, South Africa
ABSTRACT: Understanding and quantifying the impact and persistence of trade events on limit order book dynamics is of critical importance for trading decisions. Specifically, the trading trajectory needs to be chosen to cause least impact with a reasonable guarantee of execution. In this paper, empirical point processes are extracted from intraday tick data which represent key liquidity demand and resiliency events. Using these point processes, trades and quotes are modelled as a mutually‐exciting four‐variate Hawkes point process with a sum‐of‐exponentials kernel. The calibrated model allows us to quantify order book resiliency in terms of expected time frame and magnitude of quote replenishment in response to a trade event. We conjecture that certain anomalous shape characteristics of empirical price impact curves can be explained by measuring quote replenishment following trades which move the mid‐quote price. By examining a period of increasing trade velocity on the Johannesburg Stock Exchange, we show that the empirically observed increase in low‐volume price impact can be explained by a lack of commensurate quote replenishment following low‐volume, price‐moving trades.
Authors: Michael Harvey Dieter Hendricks
When: Wednesday, 16 December 2015, 16h10, Room 3