Evolving ab initio trading strategies in heterogeneous environments

12/19/2019
by   David Rushing Dewhurst, et al.
20

Securities markets are quintessential complex adaptive systems in which heterogeneous agents compete in an attempt to maximize returns. Species of trading agents are also subject to evolutionary pressure as entire classes of strategies become obsolete and new classes emerge. Using an agent-based model of interacting heterogeneous agents as a flexible environment that can endogenously model many diverse market conditions, we subject deep neural networks to evolutionary pressure to create dominant trading agents. After analyzing the performance of these agents and noting the emergence of anomalous superdiffusion through the evolutionary process, we construct a method to turn high-fitness agents into trading algorithms. We backtest these trading algorithms on real high-frequency foreign exchange data, demonstrating that elite trading algorithms are consistently profitable in a variety of market conditions—even though these algorithms had never before been exposed to real financial data. These results provide evidence to suggest that developing ab initio trading strategies by repeated simulation and evolution in a mechanistic market model may be a practical alternative to explicitly training models with past observed market data.

READ FULL TEXT

page 6

page 16

page 17

page 18

page 19

page 20

research
02/02/2023

Towards Evology: a Market Ecology Agent-Based Model of US Equity Mutual Funds II

Agent-based models (ABMs) are fit to model heterogeneous, interacting sy...
research
10/27/2019

Deep convolutional autoencoder for cryptocurrency market analysis

This study attempts to analyze patterns in cryptocurrency markets using ...
research
01/17/2018

The Data Market: Policies for Decentralised Visual Localisation

This paper presents a mercantile framework for the decentralised sharing...
research
04/26/2019

ABIDES: Towards High-Fidelity Market Simulation for AI Research

We introduce ABIDES, an Agent-Based Interactive Discrete Event Simulatio...
research
03/24/2022

Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies

Machine learning driven trading strategies have garnered a lot of intere...
research
12/13/2018

Selection mechanism design affects volatility in a market of evolving zero-intelligence agents

Financial asset markets are sociotechnical systems whose constituent age...
research
12/13/2018

Selection mechanisms affect volatility in evolving markets

Financial asset markets are sociotechnical systems whose constituent age...

Please sign up or login with your details

Forgot password? Click here to reset