Stock Portfolio Management by Using Fuzzy Ensemble Deep Reinforcement Learning Algorithm

Abstract

The research objective of this article is to train a computer (agent) with market information data so it can learn trading strategies and beat the market index in stock trading without having to make any prediction on market moves. The approach assumes no trading knowledge, so the agent will only learn from conducting trading with historical data. In this work, we address this task by considering Reinforcement Learning (RL) algorithms for stock portfolio management. We first generate a three-dimension fuzzy vector to describe the current trend for each stock. Then the fuzzy terms, along with other stock market features, such as prices, volumes, and technical indicators, were used as the input for five algorithms, including Advantage Actor-Critic, Trust Region Policy Optimization, Proximal Policy Optimization, Actor-Critic Using Kronecker Factored Trust Region, and Deep Deterministic Policy Gradient. An average ensemble method was applied to obtain trading actions. We set SP100 component stocks as the portfolio pool and used 11 years of daily data to train the model and simulate the trading. Our method demonstrated better performance than the two benchmark methods and each individual algorithm without fuzzy extension. In practice, real market traders could use the trained model to make inferences and conduct trading, then retrain the model once in a while since training such models is time0consuming but making inferences is nearly simultaneous.

Uma Estratégia para Alocação de Carteira de Ações usando Algoritmos de Aprendizado de Máquina e Regras Fuzzy

“…Em [Hao et al 2023] os autores tratam a tarefa de gerenciamento de portifólios por uma abordagem distinta da utilizada neste artigo, considerando algoritmos de Aprendizado por Reforc ¸o. O objetivo é treinar um agente com informac ¸ões de mercado para que ele aprenda estratégias de negociac ¸ão e venc ¸a o índice de mercado sem precisar fazer nenhuma previsão sobre os movimentos do mercado.…”

Proactive Mission Planning of Unmanned Aerial Vehicle Fleets Used in Offshore Wind Farm Maintenance

“…); simulation models (used to de-termine the trajectory of UAV flight ship routes, etc. ); and artificial intelligence models and fuzzy models (using, e.g., population algorithms such as ant colony [29], beetle swarm [30], and system-improved grey wolf optimization [31], as well as fuzzy logic algorithms such as fuzzy reinforcement learning [32], fuzzy particle swarm optimization [33,34], and fuzzy C-means [35]). Formal representations of these models implemented in the relevant methods of imperative programming allow for formulating and solving problems related to the so-called analysis of a problem situation, i.e., related to the search for an answer to the question of whether (what) set values of a set of decision variables guarantee a specific (extreme) value of the assumed objective function.…”