隨著新冠疫情的肆虐，遠距教學、居家辦公改變了人們的生活型態，也帶動半導體市場的大量需求。在先前的研究中，我們得知加權範數懲罰函數能有效地增加投資組合的稀疏性(sparsity)，避免了極端權重的問題，並改善投資組合的績效表現。本研究將針對新冠疫情期間，以台灣半導體產業為資產標的所建構出的加權範數最小變異投資組合作實證研究，以十項績效衡量指標為基準，並將之與1/N投資組合、全局最小變異數投資組合、限制賣空最小變異數投資組合做比較。

研究結果顯示，透過調整懲罰參數權重𝛼值有助建構最佳加權範數最小變異投資組合，且加權範數最小變異投資組合在疫情期間能有效控制風險，並擁有穩定的績效表現。加入目標限制條件無法改善加權範數最小變異投資組合之績效，而替代懲罰函數的投資組合在新冠疫情期間則擁有優異於加權範數最小變異投資組合的績效表現。

Distance learning and working from home had become the new trend since the outbreak of COVID-19, leading to strong demand for semiconductors. According to the previous research, we knew that the weighted-norm penalty increases the sparsity of the portfolio, and it could also avoid the problem of extreme weights. Hence, this research focused on the empirical study of constructing Weighted-Norm Minimum Variance Portfolio (WNMVP) with Taiwan’s semiconductor industry as the asset target during Covid-19.

In this research, we compared WNMVP with Equally-Weighted Portfolio, Global Minimum Variance Portfolio, and the No-Shortsale Minimum Variance Portfolio, and measured their performance with 10 indicators. Our results showed that adjusting the penalty parameter helped construct the optimal WNMVP, which could effectively manage risk and led to steady performance during COVID-19. Second, adding a target return constraint on WNMVP did not improve the portfolio’s performance. However, the portfolios constructed by the alternative norm penalty parameters outperformed WNMVP in this period.

1. 莊丹華(2017)。加權範數最小變異數投資組合之實證應用:以台灣股市為例。國立政治大學國際經營與貿易學系研究所未出版之碩士論文。
2. 陳睦宜(2021)。加權範數懲罰函數之實證應用:以中美貿易戰前後期間之台灣 5G供應鏈產業為例。國立政治大學國際經營與貿易學系研究所未出版之碩士論文。
3. 蔡宛廷(2021)。以範數懲罰函數建構之投資組合實證研究:以新冠肺炎區間為例。國立政治大學國際經營與貿易學系研究所未出版之碩士論文。
4. Best, M.J. and Grauer, R.R. (1991). On the Sensitivity of Mean-Variance-Efficient Portfolios to Changes in asset Means: Some Analytical and Computational Results. The Review of Economic Studies, 4(2), 315-342.
5. Black, F. and Litterman, R. (1992). Global Portfolio Optimalization. Financial Analysts Journal, 48, no.5, 28-43.
6. Brodie, J., I. Daubechies, C. D. Mol, D. Giannone, and I. Loris. (2009). Sparse and stable Markowitz portfolios. Proceedings of the National Academy of Sciences of the United States of America, 106, 12267-12272.
7. Brown, S.J. (1976). Optimal Portfolio Choice Under Uncertainty: A Bayesian approach. Ph.D. Dissertation. University of Chicago.
8. Clarke, R.G., de Silva, H., and Thorley, S. (2006). Minimum-Variance Portfolios in the U.S. Equity Market. The Journal of Portfolio Management, 33, 10-24.
9. Chopra, V.K. and Ziemba, W.T. (1993). The Effect of Errors in Means, Variances, and Covariances on Optimal Portfolio Choice. The Journal of Portfolio Management, 19(2), 6-11.
10. DeMiguel, V., Garlappi L., Nogales F. J., and Uppal, R. (2009a). A generalized approach to portfolio optimization: Improving performance by constraining portfolio norms. Management Science, 55, 798-812.
11. DeMiguel, V., Garllappi, L. and Uppal, R. (2009b). Optimal versus naive diversification strategies: How efficient is the 1/N portfolio strategy?. Review of Financial Studies, 22(5).1915-1953.
12. Duchin, R. and Levy, H. (2009). Markowitz Versus the Talmudic Portfolio Diversification Strategies. The Journal of Portfolio Management, 35(2), 71-74.
13. Fan, J., Zhang, J. and Yu, K. (2009). Asset allocation and risk assessment with gross exposure constraints for vast portfolios. Tech. rep., Princeton University.
14. Jobson, J.D. and Korkie, B. (1980). Estimation for Markowitz Efficient Portfolios. Journal of the American Statistical Association. Vol.75, No.371, 544-554.
15. Markowitz, H. (1952). Portfolio Selection, Journal of Finance, 7(1), 77-91.
16. Tobin, J. (1958). Liquidity Preference as Behavior Towards Risk. The Review of Economic Studies, Vol. 25, No.2, 65-86.
17. Welsch, R. E. and Zhou X. (2007). Application of robust statistics to asset allocation models. Revstat, 5, 97-114.
18. World Semiconductor Trade Statistic. (2021). WSTS Semiconductor Market Forecast Fall 2021.
19. Yen, Y.M. (2015). Sparse Weighted-Norm Minimum Variance Portfolio. Review of Finance, 20(3), 1259-1287.