Biblio

In financial markets, the variance of stock returns plays an important role to reduce a risk, and daily volatility is often used as one of its measurement. We in this paper focus on Realized Volatility (RV), which is one of the most well-known volatility index. Traditionally regression models have been widely used to estimate it, but Genetic Programming (GP) approaches have been proposed recent years. While regression models estimate a suitable equation for forecasting RV, GP approaches estimate a tree (individual) that consists of economic information. Through evolution process, effective economic information can survive, so GP approaches can not only estimate RV values, but also extract effective information. However, GP approaches need computational efforts to avoid premature convergence. In this paper, we proposed a mutation-base GP approach for RV estimation, and analyze which economic information is needed to estimate RV accurately.

This paper develops an opposition-based learning harmony search algorithm with mutation (OLHS-M) for solving global continuous optimization problems. The proposed method is different from the original harmony search (HS) in three aspects. Firstly, opposition-based learning technique is incorporated to the process of improvisation to enlarge the algorithm search space. Then, a new modified mutation strategy is instead of the original pitch adjustment operation of HS to further improve the search ability of HS. Effective self-adaptive strategy is presented to fine-tune the key control parameters (e.g. harmony memory consideration rate HMCR, and pitch adjustment rate PAR) to balance the local and global search in the evolution of the search process. Numerical results demonstrate that the proposed algorithm performs much better than the existing improved HS variants that reported in recent literature in terms of the solution quality and the stability.