Dynamic portfolio rebalancing through reinforcement learning

Portfolio managements in financial markets involve risk management strategies and opportunistic responses to individual trading behaviours. Optimal portfolios constructed aim to have a minimal risk with highest accompanying investment returns, regardless of market conditions. This paper focuses on providing an alternative view in maximising portfolio returns using Reinforcement Learning (RL) by considering dynamic risks appropriate to market conditions through dynamic portfolio rebalancing. The proposed algorithm is able to improve portfolio management by introducing the dynamic rebalancing of portfolios with vigorous risk through an RL agent. This is done while accounting for market conditions, asset diversifications, risk and returns in the global financial market. Studies have been performed in this paper to explore four types of methods with variations in fully portfolio rebalancing and gradual portfolio rebalancing, which combine with and without the use of the Long Short-Term Memory (LSTM) model to predict stock prices for adjusting the technical indicator centring. Performances of the four methods have been evaluated and compared using three constructed financial portfolios, including one portfolio with global market index assets with different risk levels, and two portfolios with uncorrelated stock assets from different sectors and risk levels. Observed from the experiment results, the proposed RL agent for gradual portfolio rebalancing with the LSTM model on price prediction outperforms the other three methods, as well as returns of individual assets in these three portfolios. The improvements of the returns using the RL agent for gradual rebalancing with prediction model are achieved at about 27.9–93.4% over those of the full rebalancing without prediction model. It has demonstrated the ability to dynamically adjust portfolio compositions according to the market trends, risks and returns of the global indices and stock assets.

Performance of the Car Carrier Shipping Sector in the Iberian Peninsula under the COVID-19 Scenario

The Iberian Peninsula represents the second European producer and the eighth world producer of vehicles in 2020. The pandemic of SARS-Cov2 introduced severe challenges for the worldwide population and for the industrial production and supply chains. The car carrier shipping sector has not been studied in depth in the Maritime Transportation and Port Logistics literature. This research pays special attention to the performance of this traffic in the Iberian Peninsula in the pre-pandemic era and under COVID-19 pandemic conditions, in which seven ports with car-carrier ship traffic in the Iberian Peninsula are analyzed. First, a dynamic portfolio analysis about how the COVID-19 pandemic affected the evolution of competitive positions of Iberian Peninsula ports is performed. Second, studies of the seasonality patterns of vehicle movements in ports of the Iberian Peninsula were carried out using time series of the periods from 2012 to 2019 and from 2012 to 2020. The Seasonal Variation Index (SVI) was employed to determine the seasonality of vehicle traffic in the periods considered and analyses were performed independently for both embarking and disembarking traffic. Important conclusions are revealed, e.g., during a year of COVID-19, the seven ports had decreased vehicle movements for disembarking traffic and only one port increased the traffic for embarking traffic. Furthermore, COVID-19 introduced important changes in the seasonality patterns of vehicle movements during the first months of the pandemic.

Asset Allocation via Machine Learning

In this paper, we document a novel machine learning-based numerical framework to solve static and dynamic portfolio optimization problems, with, potentially, an extremely large number of assets. The framework proposed applies to general constrained optimization problems and overcomes many major difficulties arising in current literature. We not only empirically test our methods in U.S. and China A-share equity markets, but also run a horse-race comparison of some optimization schemes documented in (Homescu, 2014). We record significant excess returns, relative to the selected benchmarks, in both U.S. and China equity markets using popular schemes solved by our framework, where the conditional expected returns are obtained via machine learning regression, inspired by (Gu, Kelly & Xiu, 2020) and (Leippold, Wang & Zhou, 2021), of future returns on pricing factors carefully chosen.

Hybrid quantum investment optimization with minimal holding period

In this paper we propose a hybrid quantum-classical algorithm for dynamic portfolio optimization with minimal holding period. Our algorithm is based on sampling the near-optimal portfolios at each trading step using a quantum processor, and efficiently post-selecting to meet the minimal holding constraint. We found the optimal investment trajectory in a dataset of 50 assets spanning a 1 year trading period using the D-Wave 2000Q processor. Our method is remarkably efficient, and produces results much closer to the efficient frontier than typical portfolios. Moreover, we also show how our approach can easily produce trajectories adapted to different risk profiles, as typically offered in financial products. Our results are a clear example of how the combination of quantum and classical techniques can offer novel valuable tools to deal with real-life problems, beyond simple toy models, in current NISQ quantum processors.

Distribution Characteristics of Multivariate Financial Assets Return based on Mathematical Model

For the non-normality and time variability of the distribution of multivariate financial assets return, a dynamic model of the distribution of multivariate financial assets return based on mathematical model is constructed in this paper. AR(1)-DCC(1,1)-GARCH(1,1) model reflects dynamic characteristics of conditional expectation and conditional variance of multivariate financial assets return. It solves the problem that restricts the in-depth research on high order dynamic portfolio optimization, which is the estimation of conditional coskewness matrix and conditional cokurtosis matrix. By constructing a multi-dimensional fluctuation model with biased t distribution, conditional asymmetric parameter and conditional free degree parameter, the distribution of multivariate financial assets return is researched. Experimental results show that the proposed model can reasonably reflect the time-varying characteristics of the multivariate stock return distribution in China’s stock market.

Identifying the Role of Gold on Sustainable Investment in Indonesia: The DCC-GARCH Approach

This research investigated the performance of a dynamic portfolio that consists of sustainable/ethical stocks and gold. The main purpose of this study is to prove that the inclusion of gold in sustainable/ethical stocks portfolios could produce better performance. Therefore, the method used in this research, DCC-GARCH, was relaxing the basic assumptions in the theory of modern portfolio that is under the assumption of the normality of stock return and securities would have constant correlation. This research used data such as SRI-KEHATI Index (SKI) and Jakarta Islamic Index (JII) in Indonesia as a proxy for sustainable investments. Additionally, this research used gold from 2013 to 2019. This study is able to provide evidence regarding the ability of a dynamic portfolio to minimize the level of portfolio risk. However, this led a lower rate of return. Based on the OLS regression, gold is also proven as a weak safe haven for sustainable investment in Indonesia. Investors who believe in ethical investment may include gold in this time-varying approach when formulating the portfolio to reduce risk significantly. The inclusion of gold in portfolios could produce hedging effectiveness. Overall, this study supports some previous findings regarding the ability of gold as an instrument, which could reduce investment risk if involved in a portfolio.

Transfer Entropy Approach for Portfolio Optimization: An Empirical Approach for CESEE Markets

In this paper, we deal with the possibility of using econophysics concepts in dynamic portfolio optimization. The main idea of the research is that combining different methodological aspects in portfolio selection can enhance portfolio performance over time. Using data on CESEE stock market indices, we model the dynamics of entropy transfers from one return series to others. In the second step, the results are utilized in simulating the portfolio strategies that take into account the previous results. Here, the main results indicate that using entropy transfers in portfolio construction and rebalancing has the potential to achieve better portfolio value over time when compared to benchmark strategies.

Portfolio Risk Management of Project Network Interdependency (on the Example of Agroholding)

The article is devoted to the problem of portfolio risk management of network project interdependencies in an agricultural company, as the lack of existing methods of project portfolio risk assessment and proper consideration of interdependencies are traced. During the study, we conducted an in-depth interview with the CFO of the company to identify the pool of ongoing projects of the company, determine the types of interproject dependencies, the likelihood of the corresponding risk in the project and the level of losses in monetary terms. Using the method of expert assessments and the noisy-OR gate tool, calculations were made in the GeNIe software product to determine the overall risk of the project portfolio after identifying high-risk projects and then recommendations were given for the application of a dynamic portfolio risk management model based on the software product used in the company.