Quantum Trader—A Multiagent-Based Quantum Financial Forecast and Trading System

Abstract

This chapter devises an innovative multiagent-based quantum financial forecast and trading system (a.k.a. quantum trader) for worldwide financial prediction and intelligent trading. Quantum trader effectively integrates quantum field signals (QFS) and quantum field oscillators (OFS) studied in Part I for neural network training and prediction into: (1) quantum forecaster—chaotic FFBP-based time-series supervised-learning agent for worldwide financial forecast and; (2) quantum trader—chaotic RBF-based actor-critic reinforcement-learning agents for the optimization of trading strategies. Quantum trader not only provides a fast reinforcement learning and forecast solution, but also it successfully resolves the massive data over-training and deadlock problems, which are usually imposed by traditional recurrent neural networks and RBF networks using classical sigmoid or Gaussian-based activation functions. From the implementation perspective, quantum trader is integrated with 2048-trading day time series financial data and 39 major financial signals as input signals for the real-time prediction and intelligent agent trading of 129 worldwide financial products which consists of: 9 major cryptocurrencies, 84 forex, 19 major commodities, and 17 worldwide financial indices. In terms of system performance, past 500-day average daily forecast performance of quantum trader attained less 1% forecast percentage errors and with promising results of 8–13% monthly average returns.