Portfolio Optimization with 2D Relative-Attentional Gated Transformer
Authors:
- 16 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Portfolio optimization is one of the most attentive fields that have been researched with machine learning approaches. Many researchers attempted to solve this problem using deep reinforcement learning due to its efficient inherence that can handle the property of financial markets. However, most of them can hardly be applicable to real-world trading since they ignore or extremely simplify the realistic constraints such as transaction costs or slippage. These constraints have a significantly negative impact on portfolio profitability. In this paper a conservative level of transaction fees and slippage are considered for the realistic experiment. To enhance the performance under those constraints, we propose a novel Deterministic Policy Gradient with 2D Relative-attentional Gated Transformer (DPGRGT) model. Applying learnable relative positional embeddings for the time and assets axes, the model better understands the peculiar structure of the financial data in the portfolio optimization domain. Also, gating layers and layer reordering are employed for stable convergence of Transformers in reinforcement learning. In our experiment using U.S. stock market data of 20 years, our model outperformed baseline models and demonstrated its effectiveness.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Reinforcement Learning in Financial MarketsData, 2019
- Self-Attention with Relative Position Representations2018
- A Simple Estimation of Bid-Ask Spreads from Daily Close, High, and Low PricesThe Review of Financial Studies, 2017
- Deep Direct Reinforcement Learning for Financial Signal Representation and TradingIEEE Transactions on Neural Networks and Learning Systems, 2016
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Learning to trade via direct reinforcementIEEE Transactions on Neural Networks, 2001
- Performance functions and reinforcement learning for trading systems and portfoliosJournal of Forecasting, 1998
- Planning and acting in partially observable stochastic domainsArtificial Intelligence, 1998
- Performance Measurement in a Downside Risk FrameworkThe Journal of Investing, 1994
- On the Theory of the Brownian MotionPhysical Review B, 1930