• 아태비즈니스연구
• /
• 제13권2호
• /
• pp.123-138
• /
• 2022

Purpose - This study compares the performances of dynamic asset allocation strategies using Korean stocks and U.S. dollar, which have been negatively correlated for a long time, to examine the diversification effects in the portfolios of them. Design/methodology/approach - In the current study, we use KOSPI200 index, as a proxy of the aggregated portfolio of Korean stocks, and USDKRW foreign exchange rate to implement various portfolio management strategies. We consider the equally-weighted, risk-parity, minimum variance, most diversified, and growth optimal portfolios for comparison. Findings - We first find the enhancement of risk adjusted returns due to risk reduction rather than return increasement for all the portfolios of consideration. Second, the enhancement is more pronounced for the trading strategies using correlations as well as volatilities compared to those using volatilities only. Third, the diversification effect has become stronger after the global financial crisis in 2008. Lastly, we find that the performance of the growth optimal portfolio can be improved by utilizing the well-known momentum phenomenon in stock markets to select the length of the sample period to estimate the expected return. Research implications or Originality - This study shows the potential benefits of adding the U.S. dollar to the portfolios of Korean stocks. The current study is the first to investigate the portfolio of Korean stocks and U.S. dollar from investment perspective.

• 충청수학회지
• /
• 제29권2호
• /
• pp.375-383
• /
• 2016

This paper investigates an optimal consumption, portfolio, and life insurance strategies of a family when there is a borrowing constraint and risk aversion change at the time of death of the breadwinner. A CRRA utility is employed and by using the dynamic programming method, we obtain analytic expressions for the optimal strategies.

• Journal of applied mathematics & informatics
• /
• 제15권1_2호
• /
• pp.109-126
• /
• 2004

This paper deals with two problems of optimal portfolio strategies in continuous time. The first one studies the optimal behavior of a firm who is forced to withdraw funds continuously at a fixed rate per unit time. The second one considers a firm that is faced with an uncontrollable stochastic cash flow, or random risk process. We assume the firm's income can be obtained only from the investment in two assets: a risky asset (e.g., stock) and a riskless asset (e.g., bond). Therefore, the firm's wealth follows a stochastic process. When the wealth is lower than certain legal level, the firm goes bankrupt. Thus how to invest is the fundamental problem of the firm in order to avoid bankruptcy. Under the case of different lending and borrowing rates, we obtain the optimal portfolio strategies for some reasonable objective functions that are the piecewise linear functions of the firm's current wealth and present some interesting proofs for the conclusions. The optimal policies are easy to be operated for any relevant investor.

• Journal of applied mathematics & informatics
• /
• 제39권1_2호
• /
• pp.215-222
• /
• 2021

We explore an optimal consumption/portfolio and retirement problem with a CARA utility function of consumption. The relevant Bellman equation for the value function is transformed into a linear equation and the optimal strategies are obtained explicitly.

• 산업공학
• /
• 제23권4호
• /
• pp.300-310
• /
• 2010

This paper is about an optimal investment portfolio strategy. Financial data of stocks, bonds, and savings from January 2. 2001 through October 30. 2009 were utilized in order to suggest the optimal portfolio strategies. Fundamental analysis and technical analysis were used in stocks-related strategy, whereas passive investment strategy and active investment strategy were used in bond-related strategy. The score is assigned to each stock index according to the suggested strategies and set trading rules are based on the scores. The simulation has been executed about each 29,400-portfolios and we figured out with the simulation result that 26.75% of 7,864 portfolios are more profitable than average stock market profit (22.6%, Annualized). The outcome of this research is summarized in two parts. First, it's the rebalancing strategy of portfolio. The result shows that value-oriented investment(long-term investment) strategy yields much higher than short-term investment strategies of stocks or active investment of bonds. Second, it's about the rebalancing cycle forming the portfolios. The result shows that the rate of return for the portfolio is the best when rebalancing cycle is 12 or 18 months.

• 품질경영학회지
• /
• 제51권4호
• /
• pp.573-588
• /
• 2023

Purpose: This study presents a research approach that utilizes deep reinforcement learning to construct optimal portfolios based on the business cycle for stocks and other assets. The objective is to develop effective investment strategies that adapt to the varying returns of assets in accordance with the business cycle. Methods: In this study, a diverse set of time series data, including stocks, is collected and utilized to train a deep reinforcement learning model. The proposed approach optimizes asset allocation based on the business cycle, particularly by gathering data for different states such as prosperity, recession, depression, and recovery and constructing portfolios optimized for each phase. Results: Experimental results confirm the effectiveness of the proposed deep reinforcement learning-based approach in constructing optimal portfolios tailored to the business cycle. The utility of optimizing portfolio investment strategies for each phase of the business cycle is demonstrated. Conclusion: This paper contributes to the construction of optimal portfolios based on the business cycle using a deep reinforcement learning approach, providing investors with effective investment strategies that simultaneously seek stability and profitability. As a result, investors can adopt stable and profitable investment strategies that adapt to business cycle volatility.

• 지능정보연구
• /
• 제20권2호
• /
• pp.59-71
• /
• 2014

KOSPI200 선물 트레이딩을 위해 업계에서는 여러 전략으로 포트폴리오를 구성해서 운용한다. 동일한 전략 모음을 갖고 있더라도 포트폴리오를 어떻게 구성하느냐에 따라 수익은 크게 차이가 난다. 시장 상황에 맞는 전략들로 포트폴리오를 구성하는 것은 오랜 경험과 탁월한 노하우가 있어야하는 어려운 작업이다. 본 논문에서는 SVM을 활용하여 쉽고 빠르게 적절한 전략 포트폴리오를 구성하는 방법을 제시하였다. 본 논문에서 제안한 시스템의 성과는 벤치마킹의 성과와 비교하여 2배 이상의 수익을 내는 것을 확인하였다. 1990.01.03~2011.11.04 동안의 KOSPI200 데이터 중 이전 80%의 데이터로 학습을 하고 최근 20%의 데이터로 성능을 시험하였다. 각 전략별로 선택여부를 판별하는 SVM모델을 만들고 그 결과를 바탕으로 포트폴리오를 구성하였다. 벤치마킹을 위해 KOSPI200 선물을 2계약 매수한 경우의 수익, 시험 시작 직전 30일간 최고 수익을 낸 2개 전략의 수익, 실제 최고 수익을 낸 전략 2개를 보유했을 때의 수익과 비교하였다. 매매 비용을 반영하지 않을 때는 벤치마킹은 132.2~510.37pt의 수익을 냈고, 본 시스템은 1072.36~1140.91pt의 수익을 보여주었다. 그리고 거래비용을 감안하면 벤치마킹은 130.44~502.41pt의 수익을 냈고, 본 시스템은 706.22pt~768.95pt의 수익을 나타내었다. 본 논문은 기계학습을 통한 전략 포트폴리오를 구성하는 방안이 유의미하며 실전에 활용할 수 있음을 보여주었다. 이를 바탕으로 여러 전략과 다양한 시장에 적용해서 안정성을 검증하면 견고한 상용 솔루션으로 발전시킬 수 있을 것이다. 그리고 자금관리 기법을 더 반영한다면 수익을 더욱 크게 향상시킬 수 있을 것이다.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.63-73
• /
• 2023

This study explores modern portfolio theory by integrating the Black-Litterman portfolio with time-series clustering, specificially emphasizing K-shape clustering methodology. K-shape clustering enables grouping time-series data effectively, enhancing the ability to plan and manage investments in stock markets when combined with the Black-Litterman portfolio. Based on the patterns of stock markets, the objective is to understand the relationship between past market data and planning future investment strategies through backtesting. Additionally, by examining diverse learning and investment periods, it is identified optimal strategies to boost portfolio returns while efficiently managing associated risks. For comparative analysis, traditional Markowitz portfolio is also assessed in conjunction with clustering techniques utilizing K-Means and K-Means with Dynamic Time Warping. It is suggested that the combination of K-shape and the Black-Litterman model significantly enhances portfolio optimization in the stock market, providing valuable insights for making stable portfolio investment decisions. The achieved sharpe ratio of 0.722 indicates a significantly higher performance when compared to other benchmarks, underlining the effectiveness of the K-shape and Black-Litterman integration in portfolio optimization.

• 대한수학회지
• /
• 제59권6호
• /
• pp.1153-1170
• /
• 2022

In this paper, we investigate the portfolio optimization problem under the SVCEV model, which is a hybrid model of constant elasticity of variance (CEV) and stochastic volatility, by taking into account of minimum-entropy robustness. The Hamilton-Jacobi-Bellman (HJB) equation is derived and the first two orders of optimal strategies are obtained by utilizing an asymptotic approximation approach. We also derive the first two orders of practical optimal strategies by knowing that the underlying Ornstein-Uhlenbeck process is not observable. Finally, we conduct numerical experiments and sensitivity analysis on the leading optimal strategy and the first correction term with respect to various values of the model parameters.

• Journal of applied mathematics & informatics
• /
• 제36권3_4호
• /
• pp.301-306
• /
• 2018

I obtain the optimal portfolio and consumption strategies of an investor who have a Cobb-Douglas utility function. And I assume that there is negative wealth constraints. This constraints mean that the investor can borrow partially against her future labor income.