Reinforcement learning is explored as a candidate machine learning technique to enhance existing analytical solutions for optimal trade execution with elements from the market microstructure. Given a volume-to-trade, xed time horizon and discrete trading periods, the aim is to adapt a given volume trajectory such that it is dynamic with respect to favourable/unfavourable conditions during realtime execution, thereby improving overall cost of trading. We consider the standard Almgren-Chriss model with linear price impact as a candidate base model. This model is popular amongst sell-side institutions as a basis for arrival price benchmark execution algorithms. By training a learning agent to modify a volume trajectory based on the market's prevailing spread and volume dynamics, we are able to improve post-trade implementation shortfall by up to 10.3% on average compared to the base model, based on a sample of stocks and trade sizes in the South African equity market.

We apply random matrix theory to compare correlation matrix estimators C obtained from emerging market data. The correlation matrices are constructed from 10 years of daily data for stocks listed on the Johannesburg Stock Exchange (JSE) from January 1993 to December 2002. We test the spectral properties of C against random matrix predictions and find some agreement between the distributions of eigenvalues, nearest neighbour spacings, distributions of eigenvector components and the inverse participation ratios for eigenvectors. We show that interpolating both missing data and illiquid trading days with a zero-order hold increases agreement with RMT predictions. For the more realistic estimation of correlations in an emerging market, we suggest a pairwise measured-data correlation matrix. For the data set used, this approach suggests greater temporal stability for the leading eigenvectors. An interpretation of eigenvectors in terms of trading strategies is given, as opposed to classification by economic sectors.

We propose the application of a high-speed maximum likelihood clustering algorithm to detect temporal financial market states, using correlation matrices estimated from intraday market microstructure features. We first determine the ex-ante intraday temporal cluster configurations to identify market states, and then study the identified temporal state features to extract state signature vectors which enable online state detection. The state signature vectors serve as low-dimensional state descriptors which can be used in learning algorithms for optimal planning in the high-frequency trading domain. We present a feasible scheme for real-time intraday state detection from streaming market data feeds. This study identifies an interesting hierarchy of system behaviour which motivates the need for timescale specific state space reduction for participating agents.

No abstract