HOẠT ĐỘNG TRONG TUẦN

Thời gian: 9h00 Thứ 3, ngày 20/08/2024

Địa điểm: Phòng 507 nhà A6

Tóm tắt: Forecasting volatility is crucial in the financial market, particularly for portfolio optimization. To enhance the accuracy of asset volatility predictions, we employ a hybrid approach that integrates Artificial Neural Networks (ANN) with GARCH-type models, supplemented by Extreme Value Theory (EVT) and Copula models, for out-of-sample return forecasting. Using this ANN-EGARCH-EVT-Copula framework, we optimize a portfolio comprising six indices from the Asian financial market, applying various Copula models. Based on performance measures such as the Sharpe and Sortino ratios, as well as Average Drawdown and Maximum Drawdown, we identify the most suitable Copula model for optimizing the portfolio.