Portfolio Selection Based on Bayesian Theory

Abstract

The traditional portfolio selection model seriously overestimates its theoretic optimal return. Aiming at this problem, two portfolio selection models are proposed to modify the parameters and enhance portfolio performance based on Bayesian theory. Firstly, a Bayesian-GARCH(1,1) model is built. Secondly, Markov Chain is applied to curve the parameters’ state transfer, and a Bayesian Markov regime-Switching-GARCH(1,1) model is constructed. Both the two models can handle the overestimation problem and can obtain self-financing portfolios. In the numerical experiments, both the models are examined with data from China stock market, and their performances are compared and analyzed. The results show that BMS-GARCH(1,1) model is superior to the Bayesian-GARCH(1,1) model.

Otimização De Carteiras Com Retornos Não Gaussianos: Uma Abordagem Bayesiana

“…Para isto compararam distribuições a priori não informativas versus as informativas, obtendo uma distribuição posterior do peso da carteira de mínima variância, usando a média e a matriz de covariância. Zhao et al (2019), mencionam que o modelo tradicional de Markowitz subestima o risco da carteira, obtendo alocações sub ótimas, portanto, os autores propõem dois modelos de seleção de carteiras para modificar os parâmetros e melhorar o rendimento da carteira desde uma abordagem Bayesiana. Estes modelos são Bayesian -GARCH e Bayesian Markov Regime Switching -GARCH sendo avaliados no mercado de valores de China, obtendo como resultado que ambos os modelos podem minimizar o problema de sobre-estimação (overfitting) e obtendo carteiras de autofinanciamento.…”

The time-varying spillover effect of China’s stock market during the COVID-19 pandemic

“…Scholars have proposed a variety of methods to characterize the co-movement of financial market. The correlation coefficient method [6] , [7] , Granger causality method [8] , Copula method [9] , [10] , spillover method [11] , [12] , [13] , [14] , [15] , [16] , [17] , transfer entropy [18] and Wavelet theory [19] are used for the research of co-movement. These methods describe and reflect the co-movement between markets from different perspectives.…”