ROBUST ASSET ALLOCATION FOR LONG-TERM TARGET-BASED INVESTING

2017 ◽  
Vol 20 (03) ◽  
pp. 1750017 ◽  
Author(s):  
P. A. FORSYTH ◽  
K. R. VETZAL
Keyword(s):  
Standard Deviation ◽  
Asset Allocation ◽  
Optimal Strategy ◽  
Stock Index ◽  
Quadratic Loss ◽  
Leverage Ratio ◽  
Terminal Wealth ◽  
Constant Proportion ◽  
Mean Variance

This paper explores dynamic mean-variance (MV) asset allocation over long horizons. This is equivalent to target-based investing with a quadratic loss penalty for deviations from the target level of terminal wealth. We provide a number of illustrative examples in a setting with a risky stock index and a risk-free asset. Our underlying model is very simple: the value of the risky index is assumed to follow a geometric Brownian motion diffusion process and the risk-free interest rate is specified to be constant. We impose realistic constraints on the leverage ratio and trading frequency. In many of our examples, the MV optimal strategy has a standard deviation of terminal wealth less than half that of a constant proportion strategy which has the same expected value of terminal wealth, while the probability of shortfall is reduced by a factor of two to three. We investigate the robustness of the model through resampling experiments using historical data dating back to 1926. These experiments also show much lower standard deviation and shortfall probability for the MV optimal strategy relative to a constant proportion strategy with approximately the same expected terminal wealth.

Dynamic mean variance asset allocation: Tests for robustness

2017 ◽  
Vol 04 (02n03) ◽  
pp. 1750021 ◽  
Author(s):  
Peter A. Forsyth ◽  
Kenneth R. Vetzal
Keyword(s):  
Asset Allocation ◽  
Stock Index ◽  
Dynamic Asset Allocation ◽  
Constant Weight ◽  
Terminal Wealth ◽  
Optimal Dynamic ◽  
Yearly Maximum ◽  
Hamilton Jacobi Bellman ◽  
Equity Index ◽  
Mean Variance

We consider a portfolio consisting of a risk-free bond and an equity index which follows a jump diffusion process. Parameters for the inflation-adjusted return of the stock index and the risk-free bond are determined by examining 89 years of data. The optimal dynamic asset allocation strategy for a long-term pre-commitment mean variance (MV) investor is determined by numerically solving a Hamilton–Jacobi–Bellman partial integro-differential equation. The MV strategy is mathematically equivalent to minimizing the quadratic shortfall of the target terminal wealth. We incorporate realistic constraints on the strategy: discrete rebalancing (yearly), maximum leverage, and no trading if insolvent. Extensive synthetic market tests and resampled backtests of historical data indicate that the multi-period MV strategy achieves approximately the same expected terminal wealth as a constant weight strategy, but with much smaller variance and probability of shortfall.

scholarly journals Artificial Intelligence Approach to Secure Pension Fund

2021 ◽  
Vol 23 (07) ◽  
pp. 110-120
Author(s):  
Safwat Saadeldin ◽  
◽  
Hegazy Zaher ◽  
Naglaa Ragaa ◽  
Heba Sayed ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Asset Allocation ◽  
Pension Fund ◽  
Planning Horizon ◽  
Return Level ◽  
Insolvency Risk ◽  
Finance Management ◽  
Portfolio Optimization Model ◽  
Mean Variance

Pension fund needs to produce a high-income return to face actuarial expectations of different kinds of benefits. An asset allocation management model of a pension fund must consider a large planning horizon because of its long-term obligations. Asset allocation controls the solvency of the fund by suitable investments and contribution policies to secure the pensioner’s future liabilities. Artificial intelligence approaches given by experts and accepted by decision-makers, provide a powerful tool for describing uncertainty. A portfolio optimization model is introduced based on variance minimization at a required return level that secures the fund against insolvency risk. This method uses an artificial Bee ColonyOptimizationApproach to the mean-variance defined by Markowitz so that future returns of the stocks are predicted where the ability of AI to improve predictive and prescriptive financial forecasting processes will change the world of finance management.

scholarly journals Macro Asset Allocation with Social Impact Investments

2019 ◽  
Vol 11 (11) ◽  
pp. 3140 ◽  
Author(s):  
Massimo Biasin ◽  
Roy Cerqueti ◽  
Emanuela Giacomini ◽  
Nicoletta Marinelli ◽  
Anna Grazia Quaranta ◽  
...  
Keyword(s):  
Risk Aversion ◽  
Asset Allocation ◽  
Social Impact ◽  
Large Fraction ◽  
Stock Index ◽  
Portfolio Risk ◽  
Risk Return ◽  
Mean Variance ◽  
Different Levels ◽  
Unique Dataset

Using a unique dataset of 50 listed companies that meet the majority of the OECD requirements for social impact investments, we construct a social impact finance stock index and investigate how investing in social impact firms can contribute to portfolio risk-return performance. We build portfolios with three different methodologies (naïve, Markowitz mean-variance optimization, GARCH-copula model), and we study the performance in terms of returns, Sharpe ratio, utility, and forecast premium based on a constant relative risk aversion function for investors with different levels of risk aversion. Consistent with the idea that social impact investment can improve portfolio risk-return performance, the results of our macro asset allocation analysis show the importance of a large fraction of investor portfolios’ stake committed to social impact investments.

Out-of-sample performance of the Black-Litterman model

2021 ◽  
pp. 29-51
Author(s):  
Frieder Meyer-Bullerdiek
Keyword(s):  
Portfolio Optimization ◽  
Portfolio Management ◽  
Asset Allocation ◽  
Jel Classification ◽  
Stock Index ◽  
Out Of Sample ◽  
Weighted Portfolio ◽  
German Stock ◽  
Mean Variance Portfolio ◽  
Mean Variance

The aim of this paper is to test the out-of-sample performance of the Black Litterman (BL) model for a German stock portfolio compared to the traditional mean-variance optimized (MV) portfolio, the German stock index DAX, a reference portfolio, and an equally weighted portfolio. The BL model was developed as an alternative approach to portfolio optimization many years ago and has gained attention in practical portfolio management. However, in the literature, there are not many studies that analyze the out-of-sample performance of the model in comparison to other asset allocation strategies. The BL model combines implied returns and subjective return forecasts. In this study, for each stock, sample means of historical returns are employed as subjective return forecasts. The empirical analysis shows that the BL portfolio performs significantly better than the DAX, the reference portfolio and the equally weighted portfolio. However, overall, it is slightly outperformed by the MV portfolio. Nevertheless, the BL portfolio may be of greater interest to investors because -according to this study, where the subjective return forecasts are based on historical returns of a rather long past period of time-it could lead in most cases to lower absolute (normalized) values for the stock weights and for all stocks to smaller fluctuations in the (normalized) weights compared to the MV portfolio. JEL classification numbers: C61, G11. Keywords: Black-Litterman, Mean-variance, Portfolio optimization, Performance.

scholarly journals EXTREMAL BEHAVIOR OF LONG-TERM INVESTORS WITH POWER UTILITY

2017 ◽  
Vol 20 (05) ◽  
pp. 1750029 ◽  
Author(s):  
NICOLE BÄUERLE ◽  
STEFANIE GRETHER
Keyword(s):  
Financial Market ◽  
Optimal Strategy ◽  
Positive Coefficient ◽  
Power Utility ◽  
Terminal Wealth ◽  
Extremal Behavior ◽  
Long Term Behavior ◽  
As If

We consider a Bayesian financial market with one bond and one stock where the aim is to maximize the expected power utility from terminal wealth. The solution of this problem is known, however there are some conjectures in the literature about the long-term behavior of the optimal strategy. In this paper, we prove that for positive coefficient in the power utility the long-term investor is very optimistic and behaves as if the best drift has been realized. In case the coefficient in the power utility is negative the long-term investor is very pessimistic and behaves as if the worst drift has been realized.

Dynamic Mean–Variance Asset Allocation

CFA Digest ◽  
2010 ◽  
Vol 40 (4) ◽  
pp. 47-49
Author(s):  
Johann U. de Villiers
Keyword(s):  
Asset Allocation ◽  
Mean Variance

Scaling and Adaptive Asset Allocation

2019 ◽  
Keyword(s):  
Asset Allocation ◽  
Investment Decision ◽  
Investment Risk ◽  
Speculative Bubbles ◽  
Time Horizons ◽  
Investment Decision Making ◽  
Time Diversification ◽  
Mean And Variance ◽  
Time Specific ◽  
Mean Variance

In this article, the author reminds us again that return mean and variance are not enough. Appropriate investment risk-bearing scales with surplus over future withdrawal commitments, as well as with investment return characteristics. This framework provides for the integration of financial planning and investment decision-making. Its time-varying risk aversion with the ratio of investments to surplus also provides an opportunity for use of dynamic strategies, though speculative bubbles require compensating inputs to avoid excessive allocation extremes. Appropriate risk-bearing can also scale with functions of shortfall probability to deal with time-specific funding requirements. The probability of avoiding shortfall from an initial surplus over longer time horizons may scale close to the square root of time, creating an illusion of time diversification. In contrast, from an initial surplus deficit, minimizing shortfall probability is akin to playing Russian roulette. Allocations based on minimized shortfall probability can be usefully blended with mean–variance allocations, especially for 5- to 15-year time horizons.

scholarly journals Cooperative Stochastic Games with Mean-Variance Preferences

Mathematics ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 230
Author(s):  
Elena Parilina ◽  
Stepan Akimochkin
Keyword(s):  
Standard Deviation ◽  
Stochastic Games ◽  
Stochastic Game ◽  
Stochastic Variable ◽  
Expected Payoff ◽  
The Core ◽  
Risk Sensitive ◽  
Payoff Functions ◽  
Cooperative Solutions ◽  
Mean Variance

In stochastic games, the player’s payoff is a stochastic variable. In most papers, expected payoff is considered as a payoff, which means the risk neutrality of the players. However, there may exist risk-sensitive players who would take into account “risk” measuring their stochastic payoffs. In the paper, we propose a model of stochastic games with mean-variance payoff functions, which is the sum of expectation and standard deviation multiplied by a coefficient characterizing a player’s attention to risk. We construct a cooperative version of a stochastic game with mean-variance preferences by defining characteristic function using a maxmin approach. The imputation in a cooperative stochastic game with mean-variance preferences is supposed to be a random vector. We construct the core of a cooperative stochastic game with mean-variance preferences. The paper extends existing models of discrete-time stochastic games and approaches to find cooperative solutions in these games.

Sign in / Sign up

Export Citation Format

Share Document