Ongoing Projects

 
Algorithmic Trading Project
The design of algorithmic trading for electronic markets and decision support systems has been the focus of attention of many studies for a diversity of market settings. It is as well known as automated trading. Algorithmic trading is a general name means employing techniques to trade in assets, such as stocks, and currencies, automatically by computers which involve the determination of a set of rules for order’s timing, price, type {Buy, Sell} and quantity to invest. In this project, we used artificial intelligent techniques such as machine learning and data mining among others to find optimal parameters to generate trading rules automatically from studying historical market data.
 
Forecasting Project
The forecasting of financial market price time series is an important research area and has been a subject of many studies. There are a number of important studies which used different methods to forecast the future price such methods are Support Vector Machines, Artificial Neural Networks (ANNs), Genetic Algorithm (GA) and Genetic Programming (GP). This project aims to develop a dynamic portfolio trading system based on GP-based forecasting model.  The results of this project can be used further to develop decision support systems and autonomous trading agent strategies for the financial market.

Completed Projects

Agent-Based FX Market Project

In this project, we use an agent-based modelling (ABM) approach to model the transactions in the Foreign Exchange (FX) market which is the most liquid financial market in the world. We first establish the statistical properties (stylized facts) of the transactions in the FX market using a unique high-frequency dataset of anonymised individual traders’ historical transactions on an account level, spanning 2.25 years. To the best of our knowledge, this dataset is the biggest available high-frequency dataset of individual FX market traders’ historical transactions. We then construct an agent-based FX market (ABFXM) which features a number of distinguishing elements including zero-intelligence directional-change event (ZI-DCT0) trading agents and asynchronous trading-time windows. The individual agents are characterised by different levels of wealth, trading time windows, different profit objectives and risk appetites and initial activation conditions. Using the identified stylized facts as a benchmark, we evaluate the trading activity reproduced from the ABFXM, and we establish that this resembles a satisfactory level the trading activity of the real FX market.

In the course of this project, we study in depth the constructed ABFXM. We focus on performing a systematic exploration of the constituent elements of the ABFXM and their impact on the dynamics of the FX market behaviour. In particular, our study explores and identifies the essential elements under which the stylized facts of the FX market trading activity are exhibited in the ABFXM. Our study suggests that the key elements are the ZI-DCT0 agents, heterogeneity which has been embedded in our model in different ways, asynchronous trading time windows, initial activation conditions and the generation of limit orders. We also show that the dynamics of the market trading activity depend on the number of agents one considers.

We explore the emergence of the stylized facts in the trading activity when the ABFXM is populated with agents with three different strategies: a variation of the zero-intelligence with a constraint (ZI-CV) strategy; the ZI-DCT0 strategy; and a genetic programming-based (GP) strategy. Our results show that the ZI-DCT0 agents best reproduce and explain the stylized facts observed in the FX market transactions data. Our study suggests that some the observed stylized facts could be the result of introducing a threshold which triggers the agents to respond to fixed periodic patterns in the price time series.
 

Directional Changes Project

Financial markets witness high levels of activity at certain times, but remain calm at others. This makes the flow of physical time discontinuous. Therefore, using physical time scales for studying financial time series runs the risk of missing important periods of activity in the markets. An alternative approach is the use of an event-based time that captures periodic activities in the market. This project describes a special type of event, called a Directional-Change (DC) event which can be used for studying financial time series. In this project, we show the potential usefulness of this approach in terms of capturing periodic market activities. We measure the length of the price curve coastline, which represents the profit potential, as defined by DC events, as well as physical time scales. Furthermore, in this project, we construct a new automated trading strategy based on the DC event approach. A series of controlled experiments were conducted aiming to study the impact of such a trading strategy on a trader’s performance.