mt5se: An Open Source Framework for Building Autonomous Trading Robots

TL;DR

This paper introduces mt5se, an open source framework for developing, backtesting, and deploying autonomous trading robots, emphasizing a multiagent architecture to improve trading performance and risk management.

Contribution

It presents a new open source framework for autonomous trading, proposes a multiagent architecture separating prediction and allocation, and discusses promising AI technologies for trading.

Findings

The framework supports development, backtesting, and live testing of trading robots.

Initial tests suggest it can aid in creating more effective trading strategies.

Discussion of architecture and technologies offers new insights for AI-based trading.

Abstract

Autonomous trading robots have been studied in artificial intelligence area for quite some time. Many AI techniques have been tested for building autonomous agents able to trade financial assets. These initiatives include traditional neural networks, fuzzy logic, reinforcement learning but also more recent approaches like deep neural networks and deep reinforcement learning. Many developers claim to be successful in creating robots with great performance when simulating execution with historical price series, so called backtesting. However, when these robots are used in real markets frequently they present poor performance in terms of risks and return. In this paper, we propose an open source framework (mt5se) that helps the development, backtesting, live testing and real operation of autonomous traders. We built and tested several traders using mt5se. The results indicate that it may help the development of better traders. Furthermore, we discuss the simple architecture that is used in many studies and propose an alternative multiagent architecture. Such architecture separates two main concerns for portfolio manager (PM) : price prediction and capital allocation. More than achieve a high accuracy, a PM should increase profits when it is right and reduce loss when it is wrong. Furthermore, price prediction is highly dependent of asset's nature and history, while capital allocation is dependent only on analyst's prediction performance and assets' correlation. Finally, we discuss some promising technologies in the area.