日內時間序列變化下動態全球資產配置

過往已有諸多研究著墨在全球資產配置(Global Asset Allocation，簡稱GAA)，而過往也利用分類系統(Extended classifier system，簡稱XCS)於演化式計算(Evolutionary Algorithm，簡稱EA)模型之中，且過往研究中也證實在總體經濟的大環境變化下XCS具有動態學習及動態調適之特性，故可使預期目標最大化。故本論文嘗試建構一個GAA-XCS投資組合模型來預測全球資產組合使配置達到收益最大化及風險最小化之目標，藉由組合各單一國家指數股票型基金(Country-Specific Exchange-Traded Fund，簡稱ETF)來做全球資產投資組合配置，利用其ETF之低成本及易交易之特性來達到資產全球風險分散。而本論文亦與傳統之買入持有投資組合策略(Buy-and-Hold)，夏普比率投資組合策略，固定比例投資組合策略(CPPI)與固定時間不變的投資組合策略(TIPP)，在不同持有時間及不同保障權重，做不同之交叉組合比較。實驗後經統計證實在95％信賴區間，GAA-XCS具有較好的收益和較低的風險相對於傳統的投資組合策略，故GAA-XCS是一能隨著時間及全球股市變化，即時改變其投資組合之動態模型即，即使在金融危機其間亦然。

關鍵字

單一國家指數股票型基金；全球資產配置；固定比例投資組合策略；固定時間不變的投資組合策略；財務時間序列

並列摘要

Several studies have been made on global asset allocation (GAA) in the past years. The extended classifier system (XCS) is built on the evolutionary algorithm (EA) model. The XCS model can learn and adapt dynamically to changes in macroeconomic environments in order for it to maximize its desired goals. This paper conducts simulation to apply XCS to GAA in country-specific exchange-traded funds (ETFs). As international stock price trends are influenced by unknown and unpredictable environments, using EA to model fluctuations in the global financial market allows for the discovery of future trend patterns, especially in high-frequency time-series global-financial data. As such, the benefits of international asset diversification can be achieved tax-efficiently with country-specific ETFs at low transaction costs and minimized tracking errors. This study attempts to build the GAA-extended classifier system (GAA-XCS) to maximize returns and minimize risks. It also compares the GAA-XCS with traditional Buy-and-Hold, Sharpe ratio portfolio, constant portion portfolio insurance (CPPI), and time invariant portfolio protection (TIPP) in a different time-varying, and different weights total 81 combinations. At the 95% confidence interval, the GAA-XCS shows better return and risk compared with traditional strategies. These empirical results indicate that GAA-XCS is capable of evolving over time; thus, it can provide a good indicator for future GAA decision making aimed at maximizing profits even during a financial crisis.

並列關鍵字

Country-specific ETFs ； Global Asset Allocation ； CPPI ； TIPP ； Financial Time Series ； K-Means

參考文獻

[2]. Fuhr, D. (2001). Exchange- traded funds: A primer. Journal of Asset Management, 3, 260–273.

[3]. Miffre, J. (2007). Country-specific ETFs: An efficient approach to global asset allocation. Journal of Asset Management, 8(2).

[4]. Karpoff, J. M. (1987). The relationship between price changes and trading volume. Journal of Financial and Quantitative Analysis, 22, 109–126

[5]. Kovacs, T. (2000). A learning classifier systems bibliography. School of Computer Science, University of Birmingham.

[7]. Eugene F. Fama and Kenneth R. French, (2004) The Capital Asset Pricing Model:Theory and Evidence,Journal of Economic Perspectives,Vol. 18, No. 3—Summer,pp. 25–46

國際替代計量

日內時間序列變化下動態全球資產配置

全文下載

主題瀏覽