Modeling the High‐Frequency FX Market: An Agent‐Based Approach

Abstract

1 AbstractThe development of computational-intelligence based strategies for electronic markets has been the focus of intense research. In order to be able to design efficient and effective automated trading strategies, one first needs to understand the workings of the market, the strategies that traders use and their interactions as well as the patterns emerging as a result of these interactions. In this paper, we develop an agent-based model of the FX market which is the market for the buying and selling of currencies. Our agent-based model of the FX market (ABFXM) comprises heterogeneous trading agents which employ a strategy that identifies and responds to periodic patterns in the price time series. We use the ABFXM to undertake a systematic exploration of its constituent elements and their impact on the stylized facts (statistical patterns) of transactions data. This enables us to identify a set of sufficient conditions which result in the emergence of the stylized facts similarly to the real market data, and formulate a model which closely approximates the stylized facts. We use a unique high frequency dataset of historical transactions data which enables us to run multiple simulation runs and validate our approach and draw comparisons and conclusions for each market setting.

Trading Strategies Optimization by Genetic Algorithm under the Directional Changes Paradigm

“…To keep up with the today's financial environment, where the high speed automated algorithms are increasingly becoming the decision makers, agents that are developed to model the trader's behaviour have been experimented with Forex instruments. With this aim, modelling the agents under a DC based trading activity, namely Z1-DCT0, into foreign exchange market was first one to be seen [16]. Further strategy improvements can be seen in DCT1 [7], and the advancement can be found in a form of higher profit at DCT1 in comparison to early attempt.…”

Designing Strategies for Autonomous Stock Trading Agents using a Random Forest Approach

“…By finding the optimal attribute sets and associations between the inputs and outputs of agent-based models, we can better understand the dynamics of financial markets and the modeled trading strategy. The financial literature includes several methods that explain and simplify the identification of attribute relationships through sampling and modeling [40][41][42][43][44].…”

Optimising Directional Changes trading strategies with different algorithms

“…Their agents used strategies known as ZI-DC0 developed by combining DC approach with trend following and contrary trading technical indicators. [9] proposed a new trading strategy called ZI-DC1 as an improvement to the study in [8]. Comparison results between ZI-DC0 and ZI-DC1 showed that ZI-DC1 was more profitable.…”