Research areas

High frequency finance

High-frequency data is the real-time record of all trading activities and their associated characteristics observed in an electronic exchange system. These "tick-by-tick" data sets provide deeper insights into the price formation process at the micro level and have been widely used to study various market microstructure issues, such as price discovery, order choice behaviour of market participants and optimal order placement strategy.

Our research in this area includes:

  • developing real-time trading platforms
  • deriving new financial econometric models for real-time data, with a special focus on the asymmetric behaviour between the supply and demand sides of the market and the information set traders refer to before submitting their orders

Agent-based computational economics

Our research in computational economics is focused on agent-based computational economics (ACE). This includes the use of artificially intelligent agents in the study of self-organising systems and risk and market-based institutions, and the design of real time trading. This also has the potential to provide policy makers and financial institutions with a powerful interactive tool to find answers for 'what-if' questions and to do 'wind tunnel tests' for market and policy design.

Computational finance

Our work is oriented to the non-Gaussian characteristics of financial markets and operational aspects of financial markets, financial engineering, portfolio and risk management. Computational methods include adaptive and reinforced learning techniques, heuristic optimisation and evolutionary computing.