Job market paper
Fully aware of the importance of effective risk management, we develop a dynamic quantile forecasting model aimed at improving the accuracy of conditional quantile predictions. We place an emphasis on the 1%, 2.5%, and 5% conditional quantiles, since these measures are often cited to manage the downside risks of portfolios. We validate that the model has a strong performance in predicting this quantile when applied to various GARCH-type models. We use conditional asymmetry measures generated from the model conditional quantile predictions to design a portfolio allocation strategy for five market indices. We identify one such strategy that could improve upon the risk-return tradeoff of the default conditional value-at-risk optimal portfolio and the equal-weight portfolio.