本文提出 MASA 多智能体自适应强化学习框架，通过协作智能体和市场观察者动态平衡收益与风险，并在三大指数10年数据上验证优势。
摘要：
近年来，深度学习或强化学习（RL）方法已被改造为反应式智能体，以便在高度动荡的金融市场环境下快速学习并作出新的投资组合管理策略。在许多情况下，由于不同金融板块之间存在极其复杂的相关性，且不同金融市场的趋势不断波动，基于深度学习或强化学习的智能体在最大化新构建投资组合的总回报时可能产生偏差，却忽视其在全球或区域板块各类市场状况动荡下的潜在风险。为此，本文提出了一个名为 MASA 的多智能体自适应框架，其中采用了复杂的多智能体强化学习（RL）方法，通过两个相互协作且具有反应能力的智能体，谨慎而动态地平衡投资组合整体回报与其潜在风险之间的权衡。此外，MASA 框架还集成了一个高度灵活且主动的智能体作为市场观察者，用于提供有关估计市场趋势的额外信息，并将其作为有价值的反馈提供给多智能体 RL 方法，以快速适应不断变化的市场状况。所得实证结果清楚表明，在过去10年沪深300（CSI 300）、道琼斯工业平均指数和标普500指数这些具有挑战性的数据集上，与许多知名的基于 RL 的方法相比，本文提出的基于多智能体 RL 方法的 MASA 框架具有潜在优势。更重要的是，本文提出的 MASA 框架为未来研究的许多可能方向提供了启示。
英文摘要：
Deep or reinforcement learning (RL) approaches have been adapted as reactive agents to quickly learn and respond with new investment strategies for portfolio management under the highly turbulent financial market environments in recent years. In many cases, due to the very complex correlations among various financial sectors, and the fluctuating trends in different financial markets, a deep or reinforcement learning based agent can be biased in maximising the total returns of the newly formulated investment portfolio while neglecting its potential risks under the turmoil of various market conditions in the global or regional sectors. Accordingly, a multi-agent and self-adaptive framework namely the MASA is proposed in which a sophisticated multi-agent reinforcement learning (RL) approach is adopted through two cooperating and reactive agents to carefully and dynamically balance the trade-off between the overall portfolio returns and their potential risks. Besides, a very flexible and proactive agent as the market observer is integrated into the MASA framework to provide some additional information on the estimated market trends as valuable feedbacks for multi-agent RL approach to quickly adapt to the ever-changing market conditions. The obtained empirical results clearly reveal the potential strengths of our proposed MASA framework based on the multi-agent RL approach against many well-known RL-based approaches on the challenging data sets of the CSI 300, Dow Jones Industrial Average and S&P 500 indexes over the past 10 years. More importantly, our proposed MASA framework shed lights on many possible directions for future investigation.
GERAD & Department of Decision Sciences, HEC Montréal（蒙特利尔高等商学院决策科学系与GERAD联合机构）；Telfer School of Management, University of Ottawa（渥太华大学特尔弗管理学院）；Evovest（伊沃维斯特）
The problem of portfolio management represents an important and challenging class of dynamic decision making problems, where rebalancing decisions need to be made over time with the consideration of many factors such as investors preferences, trading environments, and market conditions. In this paper, we present a new portfolio policy network architecture for deep reinforcement learning (DRL)that can exploit more effectively cross-asset dependency information and achieve better performance than state-of-the-art architectures. In particular, we introduce a new property, referred to as \textit{a…
Solving portfolio management problems using deep reinforcement learning has been getting much attention in finance for a few years. We have proposed a new method using experts signals and historical price data to feed into our reinforcement learning framework. Although experts signals have been used in previous works in the field of finance, as far as we know, it is the first time this method, in tandem with deep RL, is used to solve the financial portfolio management problem. Our proposed framework consists of a convolutional network for aggregating signals, another convolutional network for …
Machine Learning algorithms and Neural Networks are widely applied to many different areas such as stock market prediction, face recognition and population analysis. This paper will introduce a strategy based on the classic Deep Reinforcement Learning algorithm, Deep Q-Network, for portfolio management in stock market. It is a type of deep neural network which is optimized by Q Learning. To make the DQN adapt to financial market, we first discretize the action space which is defined as the weight of portfolio in different assets so that portfolio management becomes a problem that Deep Q-Networ…
In this paper, we implement three state-of-art continuous reinforcement learning algorithms, Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO) and Policy Gradient (PG)in portfolio management. All of them are widely-used in game playing and robot control. What's more, PPO has appealing theoretical propeties which is hopefully potential in portfolio management. We present the performances of them under different settings, including different learning rates, objective functions, feature combinations, in order to provide insights for parameters tuning, features selectio…
Portfolio management is the decision-making process of allocating an amount of fund into different financial investment products. Cryptocurrencies are electronic and decentralized alternatives to government-issued money, with Bitcoin as the best-known example of a cryptocurrency. This paper presents a model-less convolutional neural network with historic prices of a set of financial assets as its input, outputting portfolio weights of the set. The network is trained with 0.7 years' price data from a cryptocurrency exchange. The training is done in a reinforcement manner, maximizing the accumul…
Traditional portfolio management methods can incorporate specific investor preferences but rely on accurate forecasts of asset returns and covariances. Reinforcement learning (RL) methods do not rely on these explicit forecasts and are better suited for multi-stage decision processes. To address limitations of the evaluated research, experiments were conducted on three markets in different economies with different overall trends. By incorporating specific investor preferences into our RL models' reward functions, a more comprehensive comparison could be made to traditional methods in risk-retu…
University of Agder（阿格德大学）；SpareBank 1 SR-Bank（SpareBank 1 SR银行）
Stock portfolio optimization is the process of continuous reallocation of funds to a selection of stocks. This is a particularly well-suited problem for reinforcement learning, as daily rewards are compounding and objective functions may include more than just profit, e.g., risk and sustainability. We developed a novel utility function with the Sharpe ratio representing risk and the environmental, social, and governance score (ESG) representing sustainability. We show that a state-of-the-art policy gradient method - multi-agent deep deterministic policy gradients (MADDPG) - fails to find the o…
The process of continuously reallocating funds into financial assets, aiming to increase the expected return of investment and minimizing the risk, is known as portfolio management. Processing speed and energy consumption of portfolio management have become crucial as the complexity of their real-world applications increasingly involves high-dimensional observation and action spaces and environment uncertainty, which their limited onboard resources cannot offset. Emerging neuromorphic chips inspired by the human brain increase processing speed by up to 1000 times and reduce power consumption b…
Generating an investment strategy using advanced deep learning methods in stock markets has recently been a topic of interest. Most existing deep learning methods focus on proposing an optimal model or network architecture by maximizing return. However, these models often fail to consider and adapt to the continuously changing market conditions. In this paper, we propose the Multi-Agent reinforcement learning-based Portfolio management System (MAPS). MAPS is a cooperative system in which each agent is an independent "investor" creating its own portfolio. In the training procedure, each agent i…
Asset allocation (or portfolio management) is the task of determining how to optimally allocate funds of a finite budget into a range of financial instruments/assets such as stocks. This study investigated the performance of reinforcement learning (RL) when applied to portfolio management using model-free deep RL agents. We trained several RL agents on real-world stock prices to learn how to perform asset allocation. We compared the performance of these RL agents against some baseline agents. We also compared the RL agents among themselves to understand which classes of agents performed better…
Financial portfolio management (PM) is one of the most applicable problems in reinforcement learning (RL) owing to its sequential decision-making nature. However, existing RL-based approaches rarely focus on scalability or reusability to adapt to the ever-changing markets. These approaches are rigid and unscalable to accommodate the varying number of assets of portfolios and increasing need for heterogeneous data. Also, RL agents in the existing systems are ad-hoc trained and hardly reusable for different portfolios. To confront the above problems, a modular design is desired for the systems t…
Zhejiang University（浙江大学）；Fudan University（复旦大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Research（IBM研究院）
Portfolio management (PM) is a fundamental financial planning task that aims to achieve investment goals such as maximal profits or minimal risks. Its decision process involves continuous derivation of valuable information from various data sources and sequential decision optimization, which is a prospective research direction for reinforcement learning (RL). In this paper, we propose SARL, a novel State-Augmented RL framework for PM. Our framework aims to address two unique challenges in financial PM: (1) data heterogeneity -- the collected information for each asset is usually diverse, noisy…
In this thesis, we develop a comprehensive account of the expressive power, modelling efficiency, and performance advantages of so-called trading agents (i.e., Deep Soft Recurrent Q-Network (DSRQN) and Mixture of Score Machines (MSM)), based on both traditional system identification (model-based approach) as well as on context-independent agents (model-free approach). The analysis provides conclusive support for the ability of model-free reinforcement learning methods to act as universal trading agents, which are not only capable of reducing the computational and memory complexity (owing to th…
Portfolio management aims at maximizing the return on investment while minimizing risk by continuously reallocating the assets forming the portfolio. These assets are not independent but correlated during a short time period. A graph convolutional reinforcement learning framework called DeepPocket is proposed whose objective is to exploit the time-varying interrelations between financial instruments. These interrelations are represented by a graph whose nodes correspond to the financial instruments while the edges correspond to a pair-wise correlation function in between assets. DeepPocket con…
Deep Reinforcement Learning Framework for Diversified Portfolio Management Across Global Equity Markets
Quantitative Finance Research Group, Faculty of Economic Sciences, University of Warsaw（经济科学学院量化金融研究组，华沙大学）；Quantitative Finance Research Group, Department of Quantitative Finance and Machine Learning, Faculty of Economic Sciences, University of Warsaw（经济科学学院量化金融与机器学习系量化金融研究组，华沙大学）
Portfolio management via reinforcement learning is at the forefront of fintech research, which explores how to optimally reallocate a fund into different financial assets over the long term by trial-and-error. Existing methods are impractical since they usually assume each reallocation can be finished immediately and thus ignoring the price slippage as part of the trading cost. To address these issues, we propose a hierarchical reinforced stock trading system for portfolio management (HRPM). Concretely, we decompose the trading process into a hierarchy of portfolio management over trade execut…
Financial portfolio management is one of the problems that are most frequently encountered in the investment industry. Nevertheless, it is not widely recognized that both Kelly Criterion and Risk Parity collapse into Mean Variance under some conditions, which implies that a universal solution to the portfolio optimization problem could potentially exist. In fact, the process of sequential computation of optimal component weights that maximize the portfolio's expected return subject to a certain risk budget can be reformulated as a discrete-time Markov Decision Process (MDP) and hence as a stoc…
Illinois Institute of Technology（伊利诺伊理工学院）；Fidelity Investments（富达投资集团）；NYU Tandon School of Engineering（纽约大学坦登工程学院）
We present a reinforcement learning approach to goal based wealth management problems such as optimization of retirement plans or target dated funds. In such problems, an investor seeks to achieve a financial goal by making periodic investments in the portfolio while being employed, and periodically draws from the account when in retirement, in addition to the ability to re-balance the portfolio by selling and buying different assets (e.g. stocks). Instead of relying on a utility of consumption, we present G-Learner: a reinforcement learning algorithm that operates with explicitly defined one-…
There is a great number of factors to take into account when building and managing an investment portfolio. It is widely believed that a proper set-up of the portfolio combined with a good, robust management strategy is the key to successful investment. In this paper, we aim at an analysis of two aspects that may have an impact on investment performance: diversity of assets and inclusion of cash in the portfolio. We also propose two new management strategies based on the MACD and RSI factors known from technical analysis. Monte Carlo simulations within the Heston model of a market are used to …
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
Portfolio management is essential for any investment decision. Yet, traditional methods in the literature are ill-suited for the characteristics and dynamics of cryptocurrencies. This work presents a method to build an investment portfolio consisting of more than 1500 cryptocurrencies covering 6 years of market data. It is centred around Topological Data Analysis (TDA), a recent approach to analyze data sets from the perspective of their topological structure. This publication proposes a system combining persistence landscapes to identify suitable investment opportunities in cryptocurrencies. …
Peking University（北京大学）；School of Mathematical Sciences, Peking University（北京大学数学科学学院）；LMEQF
We develop a novel approach to explain why AdaBoost is a successful classifier. By introducing a measure of the influence of the noise points (ION) in the training data for the binary classification problem, we prove that there is a strong connection between the ION and the test error. We further identify that the ION of AdaBoost decreases as the iteration number or the complexity of the base learners increases. We confirm that it is impossible to obtain a consistent classifier without deep trees as the base learners of AdaBoost in some complicated situations. We apply AdaBoost in portfolio ma…
Portfolio management problems are often divided into two types: active and passive, where the objective is to outperform and track a preselected benchmark, respectively. Here, we formulate and solve a dynamic asset allocation problem that combines these two objectives in a unified framework. We look to maximize the expected growth rate differential between the wealth of the investor's portfolio and that of a performance benchmark while penalizing risk-weighted deviations from a given tracking portfolio. Using stochastic control techniques, we provide explicit closed-form expressions for the op…
One of the reasons that higher order moment portfolio optimization methods are not fully used by practitioners in investment decisions is the complexity that these higher moments create by making the optimization problem nonconvex. Many few methods and theoretical results exists in the literature, but the present paper uses the method of successive convex approximation for the mean-variance-skewness problem.
It is widely known that the common risk-factors derived from PCA beyond the first eigenportfolio are generally difficult to interpret and thus to use in practical portfolio management. We explore a alternative approach (HPCA) which makes strong use of the partition of the market into sectors. We show that this approach leads to no loss of information with respect to PCA in the case of equities (constituents of the S&P 500) and also that the associated common factors admit simple interpretations. The model can also be used in markets in which the sectors have asynchronous price information, suc…
This paper introduces a new functional optimization approach to portfolio optimization problems by treating the unknown weight vector as a function of past values instead of treating them as fixed unknown coefficients in the majority of studies. We first show that the optimal solution, in general, is not a constant function. We give the optimal conditions for a vector function to be the solution, and hence give the conditions for a plug-in solution (replacing the unknown mean and variance by certain estimates based on past values) to be optimal. After showing that the plug-in solutions are sub…
We give a detailed account of correlations between credit sector/quality and treasury curve factors, using the robust framework of the Barclays POINT Global Risk Model. Consistent with earlier studies, we find a strong negative correlation between sector spreads and rate shifts. However, we also observe that the correlations between spreads and Treasury twists reversed recently, which is likely attributable to the Fed's ongoing quantitative easing. We also find that short-term effective durations in the banking industry are now significantly lower than historical patterns would indicate. Our f…
This work proposes a novel portfolio management technique, the Meta Portfolio Method (MPM), inspired by the successes of meta approaches in the field of bioinformatics and elsewhere. The MPM uses XGBoost to learn how to switch between two risk-based portfolio allocation strategies, the Hierarchical Risk Parity (HRP) and more classical Naïve Risk Parity (NRP). It is demonstrated that the MPM is able to successfully take advantage of the best characteristics of each strategy (the NRP's fast growth during market uptrends, and the HRP's protection against drawdowns during market turmoil). As a res…
In this paper, we document a novel machine learning based bottom-up approach for static and dynamic portfolio optimization on, potentially, a large number of assets. The methodology applies to general constrained optimization problems and overcomes many major difficulties arising in current optimization schemes. Taking mean-variance optimization as an example, we no longer need to compute the covariance matrix and its inverse, therefore the method is immune from the estimation error on this quantity. Moreover, no explicit calls of optimization routines are needed. Applications to equity portfo…
Managing investment portfolios is an old and well know problem in multiple fields including financial mathematics and financial engineering as well as econometrics and econophysics. Multiple different concepts and theories were used so far to describe methods of handling with financial assets, including differential equations, stochastic calculus and advanced statistics. In this paper, using a set of tools from the probability theory, various strategies of building financial portfolios are analysed in different market conditions. A special attention is given to several realisations of a so cal…
This paper describes multi-portfolio `internal' rebalancing processes used in the finance industry. Instead of trading with the market to `externally' rebalance, these internal processes detail how portfolio managers buy and sell between their portfolios to rebalance. We give an overview of currently used internal rebalancing processes, including one known as the `banker' process and another known as the `linear' process. We prove the banker process disadvantages the nominated banker portfolio in volatile markets, while the linear process may advantage or disadvantage portfolios. We describe a…
Deep reinforcement learning (DRL) has been widely studied in the portfolio management task. However, it is challenging to understand a DRL-based trading strategy because of the black-box nature of deep neural networks. In this paper, we propose an empirical approach to explain the strategies of DRL agents for the portfolio management task. First, we use a linear model in hindsight as the reference model, which finds the best portfolio weights by assuming knowing actual stock returns in foresight. In particular, we use the coefficients of a linear model in hindsight as the reference feature wei…
With the improvement of computer performance and the development of GPU-accelerated technology, trading with machine learning algorithms has attracted the attention of many researchers and practitioners. In this research, we propose a novel portfolio management strategy based on the framework of Deep Deterministic Policy Gradient, a policy-based reinforcement learning framework, and compare its performance to that of other trading strategies. In our framework, two Long Short-Term Memory neural networks and two fully connected neural networks are constructed. We also investigate the performance…
We propose a long term portfolio management method which takes into account a liability. Our approach is based on the LQG (Linear, Quadratic cost, Gaussian) control problem framework and then the optimal portfolio strategy hedges the liability by directly tracking a benchmark process which represents the liability. Two numerical results using empirical data published by Japanese organizations are served: simulations tracking an artificial liability and an estimated liability of Japanese organization. The latter one demonstrates that our optimal portfolio strategy can hedge his or her liability…
