Multi-period Portfolio Research Articles

Multiperiod Dynamic Portfolio Choice: When High Dimensionality Meets Return Predictability

Multiperiod portfolio choice is the central problem in active asset management. Multiperiod dynamic portfolios are notoriously difficult to solve, especially when there are hundreds of tradable assets as well as a large number of state variables. In this article, we develop a novel two-step methodology to solve the multiperiod dynamic portfolio choice problem with high dimensional assets in the presence of return predictability conditional on a large number of state predictors. Specifically, in the first step, we propose the new Risk-Premium Projected-PCA (RP-PPCA) method to reduce the dimension of tradable assets. This method achieves Dimension Reduction (DR) by estimating latent factors with explanatory power in both time series variation and expected return in high-dimension-low-sample-size data. In the second step, we use dynamic programming to solve the multiperiod portfolio choice problem, and in each recursive step, we adopt an Adjusted semiparametric Model Averaging (AMA) method to avoid the curse of dimensionality associated with a large set of state variables while remaining computationally efficient. Thus, we name this two-step approach DRAMA, which stands for a combination of a new dimension reduction method and an adjusted semiparametric model averaging method. Analytically, we show that the portfolios constructed by the DRAMA are approximately optimal under mild assumptions. Moreover, our numerical results based on empirical data from US stock markets show that the proposed portfolios have excellent out-of-sample performances.

Can multi-period auto-portfolio systems improve returns? Evidence from Chinese and U.S. stock markets

Current portfolios often underperform due to limited utilization of stock selection and a lack of attention to multi-period trading. To address this issue, we propose an auto-portfolio system that addresses these problems by integrating multi-class stock selection with portfolio optimization based on technical indicators. For stock selection, we combine Two-dimensional Convolutional Neural Network with Long and Short-term Memory to forecast the future trends of stocks and select potentially profitable stocks for investment. We then develop two portfolio models based on two technical indicators, which automatically perform multi-period investment. We establish a many-objective optimization problem including return, Conditional Value-at-Risk, skewness, kurtosis, and cost. To solve the optimization problem, we employ Non-dominated Sorting Genetic Algorithm III. The data of Chinese and the U.S. stock markets is used for verification, and a comparative analysis is discussed. In the out-of-sample period, two proposed multi-period portfolio models outperform the other models in both single and multi period, achieving higher Sharpe ratio of 1.021 and 1.052 in China, and 1.116 and 1.236 in the U.S., respectively.

DivFolio: a Shiny application for portfolio divestment in green finance wealth management

Abstract This paper introduces DivFolio, a multiperiod portfolio selection and analytic software application that incorporates automated and user-determined divestment practices accommodating Environmental Social Governance (ESG) and portfolio carbon footprint considerations. This freely available portfolio analytics software tool is written in R with a GUI interface developed as an R Shiny application for ease of user experience. Users can utilize this software to dynamically assess the performance of asset selections from global equity, exchange-traded funds, exchange-traded notes, and depositary receipts markets over multiple time periods. This assessment is based on the impact of ESG investment and fossil-fuel divestment practices on portfolio behavior in terms of risk, return, stability, diversification, and climate mitigation credentials of associated investment decisions. We highlight two applications of DivFolio. The first revolves around using sector scanning to divest from a specialized portfolio featuring constituents of the FTSE 100. The second, rooted in actuarial considerations, focuses on divestment strategies informed by environmental risk assessments for mixed pension portfolios in the US and UK.

Multi-period portfolio choice under loss aversion with dynamic reference point in serially correlated market

This paper explores a novel multi-period portfolio decision model for loss-averse investors with dynamically adapted reference points in a market with serially correlated returns. We demonstrate that the optimal policy is a piecewise linear function of the deviation between current wealth and reference level, and its slopes are a path-dependent function of the historical returns, in sharp contrast to the constant slopes generated by the simplified model that ignores the diminishing sensitivity and assumes independent returns. This distinctive characteristic significantly departs from the conventional V-shaped pattern of the risky position, leading to a more intricate nonlinear functional mapping. Our study underscores the potential pitfalls of relying on the simplified model and offers valuable insights for investors and practitioners seeking to formulate effective portfolio strategies under realistic market conditions. Furthermore, our simulation analysis indicates that the predictability of returns, coupled with a slight degree of diminishing sensitivity, may amplify the disposition effect. Lastly, we establish that the new policy also effectively addresses the multi-period mean-conditional-value-at-risk (CVaR) portfolio optimization problem in the context of correlated returns, thereby expanding the practical applications of our findings.

Learning fused lasso parameters in portfolio selection via neural networks

In recent years, fused lasso models are becoming popular in several fields, such as computer vision, classification and finance. In portfolio selection, they can be used to penalize active positions and portfolio turnover. Despite efficient algorithms and software for solving non-smooth optimization problems have been developed, the amount of regularization to apply is a critical issue, especially if we have to achieve a financial aim. We propose a data-driven approach for learning the regularization parameters in a fused lasso formulation of the multi-period portfolio selection problem, able to realize a given financial target. We design a neural network architecture based on recurrent networks for learning the functional dependence between the regularization parameters and the input data. In particular, the Long Short-Term Memory networks are considered for their ability to process sequential data, such as the time series of the asset returns. Numerical experiments performed on market data show the effectiveness of our approach.

An uncertainty theory based tri-objective behavioral portfolio selection model with loss aversion and reference level using a modified evolutionary root system growth algorithm

The outbreak of uncertain events, e.g., financial crisis, regional conflict and abrupt contagion, has a significant impact on residents’ income. Hence, the wealth management and portfolio selection become more and more important. In addition, the behavioral finance believes that decision-making process of the investors not only depend on utility maximization, but also on who to compare with. It differs from the traditional finance based on rational cognitive acquiring and decision-making of agents, in this paper, we consider both investment uncertainty and investment utility with reference level for portfolio selection. First, we introduce the uncertainty theory and loss aversion utility with reference level based on behavioral finance. Then we study an uncertain multi-period portfolio selection problem. Moreover, we formulate an uncertain behavioral portfolio selection model with three objective functions for which we propose an equivalent program consisting of a main model and two auxiliary models for tri-objective optimization model. Thereafter, we use a modified evolutionary root system growth algorithm to solve the transformed models. Finally, a numerical simulation allows to show the practicability of proposed models and validity of modified algorithm.

The cost of delay as risk measure in target-based multi-period portfolio selection models

Abstract Accepted by: Aris Syntetos Increasingly, in recent years, the fund management industry has evolved towards so-called goal-based investing paradigms, under which investors are assumed to base their portfolio strategies on pre-specified targets to be attained in the future. A similar decision model is common in the wealth management and the life insurance industries where targets may be associated with long-term investment horizons and retirement planning problems. Based on this evidence, we propose in this article a novel risk measure explicitly focusing on the financial cost that may be associated with a delay in reaching those targets. We show that the definition of this risk measure is both rather natural and effective to capture investors’ risk preferences. A dynamic portfolio selection model is developed to assess the effectiveness of the risk measure from financial and risk control perspectives. The introduced risk measure has good properties and it is related to the Value-at-Risk with a given confidence level. Under sufficiently general statistical assumptions, we derive a closed form solution to a mean-risk formulation of the portfolio problem in which the cost of delay is taken as risk measure. Finally, a set of numerical tests validate the proposed portfolio selection model and show a set of comparative results with respect to a classical dynamic mean-variance model.

A Distributed Event-Triggered Approach for Decentralized Multi-Period Portfolio Optimization via the Alternating Direction Method of Multipliers

A Distributed Event-Triggered Approach for Decentralized Multi-Period Portfolio Optimization via the Alternating Direction Method of Multipliers

Responsible Investing: A Multi-period Portfolio Selection Model

Responsible Investing: A Multi-period Portfolio Selection Model

Multiperiod portfolio allocation: A study of volatility clustering, non-normalities and predictable returns

This paper examines the dynamic, multiperiod portfolio choices of an investor facing predictable returns with volatility clustering and non-normalities, two pervasive stock return data characteristics. With a portfolio of one risk-free and one risky asset, we calibrate the model to the U.S. stock market and consider multiperiod choices, GARCH volatilities and Johnson-distributed non-normal errors. Quadrature techniques are used to determine the optimal allocation of the risky asset. The results show that accounting for volatility clustering strongly reduces the large hedging demands typically obtained with predictable returns. Non-normalities have modest impacts on allocations. Out-of-sample tests reveal that despite the changes in allocation observed in many cases, little statistical evidence is found that the Certainty Equivalent returns are impacted by multiperiod portfolios, nor by portfolios based on non-normal error.

Regularization methods for sparse ESG-valued multi-period portfolio optimization with return prediction using machine learning

In the context of global sustainable development, environmental, social, and governance (ESG) investment has become a frontier topic in the field of asset management. This paper focuses on ESG-valued multi-period portfolio selection problem which incorporates ESG factor into traditional portfolio optimization. Using ESG-valued returns instead of traditional returns, we propose an ESG-valued fused LASSO model to promote an optimal sparse multi-period portfolio strategy. The objective of the model is to minimize a combination of returns and risks with respect to ESG ratings based on classical Markowitz mean–variance framework. The sparsity of the portfolio at each period and the turnover across periods is achieved by the ℓ1 regularization approach. To improve the out-of-sample performance of the ESG-valued model, we introduce two machine learning methods, namely random forest and support vector regression, to predict the ESG-valued returns. We develop a symmetric alternating direction method of multipliers to solve the regularized optimization model. Additionally, some other sparsity-driven penalty functions are discussed which results in a general framework of multi-period portfolio optimization. Finally, numerical experiments on several real datasets from both in-sample and out-of-sample demonstrate the positive effect of ESG in multi-period portfolio optimization.

Multi-Period Portfolio Optimization under Cash-In Strategies

Portfolio optimization has been crucial in its applications to finance. Investors allocate capital in terms of various assets and wisely adjust each proportion in quest of higher returns and lower risks. However, common optimization strategies are usually short- sighted, lacking the ability of gaining higher returns over a long period. This paper addresses Multi-Period Portfolio Optimization problem in more applicable settings to provide efficient strategies. Firstly, a summary of conclusions from former works and scholars is given. Since most previous works assume self-financing conditions, this work extends this constraint and considers more complex cash-in and cash-out situations. It also derives the expression of the optimal policy for trading at each period as well as the objective functions. Finally, numerical experiments are done under both self-financing and cash-in situations to prove the validity of conclusions. This work has profound implications in finance because it adopts conditions more consistent with real-world scenarios and provides more farsighted strategies. Moreover, the solution offers a prototype for similar optimization in other fields like electrical engineering and stochastic processes.

Multi-period power utility optimization under stock return predictability

In this paper, we derive an analytical solution to the dynamic optimal portfolio choice problem in the case of an investor equipped with a power utility function of wealth. The results are established by solving the Bellman backward recursion under the assumption that the vector of asset returns follows a vector-autoregressive process with predictable variables. In an empirical study, the performance of the derived solution is compared with the one obtained by applying the numerical method. The comparison is performed in terms of the final wealth and its expected utility. It is documented that the application of the analytical solution to the multi-period portfolio choice problem leads to higher values of both the final wealth and the expected utility.

Multi-criteria fuzzy portfolio selection based on three-way decisions and cumulative prospect theory

Portfolio selection is one of the hottest issue in decision-making and management engineering. But due to the capital market natural complexity and investors’ irrational behaviors, it is not easy for investors to achieve their predefined goals. In this study, we propose a novel three-way decisions model based on cumulative prospect theory and outranking relations. Compared with traditional two-way decisions, the introduction of a boundary region into the three-way decisions theory makes it possible to reduce decision risk. By constructing an outranked set for each alternative and a hybrid multi-criteria decision-making matrix, three strategies are proposed by us to design the three-way decisions model. In order to test the effectiveness of the proposed model, we introduce it into a fuzzy multi-period portfolio selection case and design an improved particle swarm optimization as the solution algorithm. Finally, the effectiveness of the algorithm is validated by some test functions. And an experiment based on real market data validates the proposed multi-period portfolio selection model outperforms other compared models in terms of return, risk and risk-adjusted criteria.

An Approach for a Multi-Period Portfolio Selection Problem by considering Transaction Costs and Prediction on the Stock Market

This paper addresses a method to solve a multi-period portfolio selection on the stock market. The portfolio problem seeks an investor to trade stocks with a finite budget and a given integer number of stocks to hold in a portfolio. The trade must be performed through a stockbroker that charges its respective transaction cost and has its minimum required trade amount. A mathematical model has been proposed to deal with the constrained problem. The objective function is to find the best risk-return rate; thus, Sharpe Ratio and Treynor Ratio are used as objective functions. The returns are the same for these ratios, but the risks are not Sharpe considering covariance and Treynor systematical risk. The returns are predicted using a Neural Net with Long-Short-Term Memory (LSTM). This neural net is compared with simple forecasting methods through Mean Absolute Percentage Error (MAPE). Computational experiments show the quality prediction performed by LSTM. The heteroskedastic risk is estimated by Generalized Autoregressive Conditional Heteroskedasticity (GARCH), adjusting the variance for every period; this risk measure is used in Sharpe Ratio. The experiment contemplates a weekly portfolio selection with 5 and 10 stocks in 122 weekly periods for each Chilean market ratio. The best portfolio is Sharpe Ratio with ten stocks, performing a 62.28% real return beating the market, represented by the Selective Stock Price Index (IPSA). Even the worst portfolio, Treynor Ratio, overcomes the IPSA cumulative yield with ten stocks.

Distributionally robust multi-period portfolio selection subject to bankruptcy constraints

<p style='text-indent:20px;'>An optimization problem with moments information which suffers from distributional uncertainty can be handled through distributionally robust optimization. In this paper, we will consider distributionally robust multi-period portfolio selection since only moment information of portfolios can be gathered in practice. We will consider two different scenarios. One is that moments information can be obtained exactly and the other one is that the moments information is also uncertain. For the two scenarios, we will show how to transform the corresponding distributionally robust optimization problem into a second order cone problem (SOCP) which can be easily solved by existing methods. Some numerical experiments are presented to demonstrate the effectiveness of our proposed method.</p>

Distributionally robust optimization with Wasserstein metric for multi-period portfolio selection under uncertainty

The mean-variance model formulated by Markowitz for a single period serves as a fundamental method of modern portfolio selection. In this study, we consider a multi-period case with uncertainty that better matches the reality of the financial market. Using the Wasserstein metric to characterize the uncertainty of returns in each period, a new distributionally robust mean-variance model is proposed to solve multi-period portfolio selection problem. We further transform the developed model into a tractable convex problem using duality theory. We also apply a nonparametric bootstrap method and provide a specific algorithm to estimate the radius of the Wasserstein ball. The effects of the parameters on the corresponding strategy and evaluation criteria of portfolios are analyzed using in-sample data. The analysis indicate that the return and risk of our portfolio selections are relatively immune to parameter values. Finally, a series of out-of-sample experiments demonstrate that the proposed model is superior to some other models in terms of final wealth, standard deviation, and Sharpe ratio.

An event-triggered iteratively reweighted convex optimization approach to multi-period portfolio selection

This paper addresses multi-period portfolio selection driven by events. We define an event-triggering function to mimic fund managers to activate sequential portfolio rebalancing and maximize Sharpe and Sortino ratios in the Markowitz’s return–risk framework. At first, the multi-period portfolio selection problem is formulated with a variable weight as a series of biconvex optimization problems with a surrogated objective function to maximize the Sharpe ratio or Sortino ratio. In each period, the portfolio optimization problem is further reformulated as an iteratively reweighted convex quadratic optimization problem. The multi-period portfolio selection problem is then solved sequentially based on a defined event-trigger function and a quadratic optimizer. The experiments are done on eight world stock markets datasets to show the capabilities of the proposed approach in calculating market indices and equal-weighted portfolios in terms of Sharpe and Sortino ratios.

Multi-period portfolio selection based on uncertainty theory with bankruptcy control and liquidity

Due to the impact of uncertain events, such as the 2008 financial crisis and the outburst of COVID-19 pandemic, the experts’ evaluations information is becoming increasingly important. This paper considers a multi-period portfolio optimization problem under uncertain circumstance, and the return rates of risky securities are regarded as uncertain variables, where the uncertainty theory is used to deal with experts’ evaluations. In light of the complexity of financial markets, we formulate an uncertain multi-period mean-entropy-variance model, where bankruptcy, liquidity, diversification and self-financing are considered as realistic constraints. Furthermore, the maximum return and the minimum risk are both achieved in a single-objective model through the normalization method. Then the equivalent deterministic forms of two secondary models for main model are provided. In addition, we develop a modified root system growth algorithm, which is more suitable for the proposed model. Finally, the effectiveness of the proposed model and designed algorithm is confirmed by numerical simulations.

Sparse Approximations with Interior Point Methods

Large-scale optimization problems that seek sparse solutions have become ubiquitous. They are routinely solved with various specialized first-order methods. Although such methods are often fast, they usually struggle with not-so-well-conditioned problems. In this paper, specialized variants of an interior point-proximal method of multipliers are proposed and analyzed for problems of this class. Computational experience on a variety of problems, namely, multiperiod portfolio optimization, classification of data coming from functional magnetic resonance imaging, restoration of images corrupted by Poisson noise, and classification via regularized logistic regression, provides substantial evidence that interior point methods, equipped with suitable linear algebra, can offer a noticeable advantage over first-order approaches.