scholarly journals Gestão de carteiras sob múltiplos regimes: Performance fora da amostra

2020 ◽  
Vol 18 (3) ◽  
pp. 52
Author(s):  
Marcelo Lewin ◽  
Carlos Heitor Campani
Keyword(s):  
Comparative Analysis ◽  
Approximate Analytical Solution ◽  
Portfolio Allocation ◽  
Dynamic Allocation ◽  
Allocation Strategy ◽  
Confidence Levels ◽  
Average Return ◽  
Multiple Regimes ◽  
Out Of Sample ◽  
Asset Classes

<p>We propose a dynamic allocation strategy for an investor which considers three unobservable economic regimes, which we estimate using returns on five Brazilian asset classes. The strategy is based on an approximate analytical solution of a realistic configuration of the economy. The out-of-sample performance exceeds those of every benchmark we consider in 6 out of 10 years, with a weekly average return significantly higher than any benchmark at the usual confidence levels. From 2010 to 2019, our strategy achieves an average return of 21.6% per annum against, for example, 9.8% p.a. of the CDI and 4.7% p.a. of the Ibovespa. In particular, a comparative analysis makes clear how important it is to include multiple regimes in portfolio allocation.</p>

scholarly journals Covariance Prediction in Large Portfolio Allocation

Econometrics ◽  
2019 ◽  
Vol 7 (2) ◽  
pp. 19 ◽  
Author(s):  
Carlos Trucíos ◽  
Mauricio Zevallos ◽  
Luiz K. Hotta ◽  
André A. P. Santos
Keyword(s):  
Minimum Variance ◽  
Portfolio Allocation ◽  
Conditional Covariance ◽  
Empirical Comparison ◽  
Information Ratio ◽  
Financial Decisions ◽  
Average Return ◽  
Out Of Sample ◽  
One Step ◽  
Sample Minimum

Many financial decisions, such as portfolio allocation, risk management, option pricing and hedge strategies, are based on forecasts of the conditional variances, covariances and correlations of financial returns. The paper shows an empirical comparison of several methods to predict one-step-ahead conditional covariance matrices. These matrices are used as inputs to obtain out-of-sample minimum variance portfolios based on stocks belonging to the S&P500 index from 2000 to 2017 and sub-periods. The analysis is done through several metrics, including standard deviation, turnover, net average return, information ratio and Sortino’s ratio. We find that no method is the best in all scenarios and the performance depends on the criterion, the period of analysis and the rebalancing strategy.

A comparison of minimum variance and maximum Sharpe ratio portfolios for mainstream investors

2022 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Anja Vinzelberg ◽  
Benjamin Rainer Auer
Keyword(s):  
Minimum Variance ◽  
Sharpe Ratio ◽  
Optimization Techniques ◽  
Estimation Methods ◽  
Content Type ◽  
Single Index ◽  
Index Model ◽  
Single Index Model ◽  
Out Of Sample ◽  
Asset Classes

PurposeMotivated by the recent theoretical rehabilitation of mean-variance analysis, the authors revisit the question of whether minimum variance (MinVar) or maximum Sharpe ratio (MaxSR) investment weights are preferable in practical portfolio formation.Design/methodology/approachThe authors answer this question with a focus on mainstream investors which can be modeled by a preference for simple portfolio optimization techniques, a tendency to cling to past asset characteristics and a strong interest in index products. Specifically, in a rolling-window approach, the study compares the out-of-sample performance of MinVar and MaxSR portfolios in two asset universes covering multiple asset classes (via investable indices and their subindices) and for two popular input estimation methods (full covariance and single-index model).FindingsThe authors find that, regardless of the setting, there is no statistically significant difference between MinVar and MaxSR portfolio performance. Thus, the choice of approach does not matter for mainstream investors. In addition, the analysis reveals that, contrary to previous research, using a single-index model does not necessarily improve out-of-sample Sharpe ratios.Originality/valueThe study is the first to provide an in-depth comparison of MinVar and MaxSR returns which considers (1) multiple asset classes, (2) a single-index model and (3) state-of-the-art bootstrap performance tests.

Microstructure in the Machine Age

2020 ◽  
Author(s):  
David Easley ◽  
Marcos López de Prado ◽  
Maureen O’Hara ◽  
Zhibai Zhang
Keyword(s):  
Machine Learning ◽  
Market Efficiency ◽  
Predictive Power ◽  
Explanatory Power ◽  
Futures Contracts ◽  
Machine Age ◽  
Price Process ◽  
Out Of Sample ◽  
Asset Classes ◽  
Out Of Sample Prediction

Abstract Understanding modern market microstructure phenomena requires large amounts of data and advanced mathematical tools. We demonstrate how machine learning can be applied to microstructural research. We find that microstructure measures continue to provide insights into the price process in current complex markets. Some microstructure features with high explanatory power exhibit low predictive power, while others with less explanatory power have more predictive power. We find that some microstructure-based measures are useful for out-of-sample prediction of various market statistics, leading to questions about market efficiency. We also show how microstructure measures can have important cross-asset effects. Our results are derived using 87 liquid futures contracts across all asset classes.

scholarly journals WHICH VARIABLES PREDICT INDONESIA'S INFLATION?

2019 ◽  
Vol 22 (1) ◽  
pp. 87-102 ◽  
Author(s):  
Susan Sunila Sharma
Keyword(s):  
Time Series ◽  
Comparative Analysis ◽  
Inflation Rate ◽  
Time Series Data ◽  
Predictor Variables ◽  
Series Data ◽  
Macroeconomic Variables ◽  
Monthly Time Series ◽  
Out Of Sample ◽  
Exhaustive List

We use an exhaustive list of Indonesia’s macroeconomic variables in a comparative analysis to determine which predictor variables are most important in forecasting Indonesia’s inflation rate. We use monthly time-series data for 30 macroeconomic variables. Using both in-sample and out-of-sample predictability evaluations, we report consistent evidence of inflation rate predictability using 11 out of 30 macroeconomic variables.

scholarly journals A comparative analysis of returns of various financial asset classes in South Africa: a triumph of bonds?

2019 ◽  
Vol 18 (3) ◽  
pp. 175-195
Author(s):  
R Vivian ◽  
C Auret
Keyword(s):  
South Africa ◽  
Comparative Analysis ◽  
Focal Point ◽  
Risk Measures ◽  
Sharpe Ratio ◽  
The Other ◽  
Financial Asset ◽  
Long Run ◽  
Popular View ◽  
Asset Classes

There is a popular view that equities always outperform other financial asset classes; especially bonds. This study investigates the performance of three common asset classes to determine whether or not this view is validated in South Africa. Conceptually, the popular view is irrational. If one class consistently and materially outperforms other asset classes, in the absence of other reasons, the other asset classes would disappear. Accordingly, rationally, in the long run and on a risk-adjusted basis, returns on all asset classes should conceptually more or less converge. The results from this study, which concentrates on equities, bonds and cash, show that in South Africa, even before adjusting for risk, there was no material difference between the returns of equities over long bonds over the 27-year period covered by this study (1986–2013). This is equally true for other shorter fixed periods with the end-date (28 February 2013) being the focal point. It is even more evident that bonds outperform equities when a system of rolling periods is used. On a nominal basis (before adjusting for risk), over any randomly selected rolling period, bonds outperform equities in six of the seven categories. This study does not take tax into consideration. After adjusting for risk using the Sharpe ratio or other risk measures, bonds outperformed equities.

Dynamic allocation strategy of VM resources with fuzzy transfer learning method

2020 ◽  
Vol 13 (6) ◽  
pp. 2201-2213 ◽  
Author(s):  
Xiang Wu ◽  
Huanhuan Wang ◽  
Wei Tan ◽  
Dashun Wei ◽  
Minyu Shi
Keyword(s):  
Transfer Learning ◽  
Learning Method ◽  
Dynamic Allocation ◽  
Allocation Strategy

Forecasting value at risk (VAR) for emerging and developed markets

2019 ◽  
Vol 37 (3) ◽  
pp. 133
Author(s):  
Viviane Naimy ◽  
Melissa Bou Zeidan
Keyword(s):  
Emerging Markets ◽  
Value At Risk ◽  
Predictive Ability ◽  
Historical Simulation ◽  
Confidence Levels ◽  
Developed Markets ◽  
Out Of Sample ◽  
Weighted Model ◽  
The One ◽  
Modelling And Forecasting

This paper explores different approaches to modelling and forecasting VaR, using both historical simulation and volatility-weighted bootstrap methods, where volatility is estimated using GARCH (1,1) and EGARCH (1,1). It examines the one day predictive ability of three historical simulation VaR models at the 90%, 95%, and 99% confidence levels for developed and emerging equity markets for the period 2011- 2017 that witnessed difficult and extreme market conditions. 870 scenarios of future returns are generated for each of the 500 days representing the out of sample period extending from March 2015 up to January 2017 in order to estimate the corresponding VaR for both markets. The GARCH (1,1) volatility-weighted model is accepted for both markets and is classified as the best performing model. The EGARCH (1,1) volatility-weighted model’s results were inconclusive; in fact, the back-test was accepted at all confidence levels for the developed markets while rejected at the 99% confidence level for the emerging markets. The basic historical simulation failed in estimating an accurate VaR for the emerging markets.

Sign in / Sign up

Export Citation Format

Share Document