• Management Science and Financial Engineering
• /
• v.10 no.1
• /
• pp.25-41
• /
• 2004

There have been many studies to build a model that can help investors construct optimal portfolio. Most of the previous models, however, are based upon the path-breaking Markowitz model (1959) which is a quantitative model. One of the most important problems with that kind of quantitative model is that, in reality, most of the investors use not only quantitative, but also qualitative information when they select their optimal portfolio. Since collecting both types of information from the markets are time consuming and expensive, making a set of target assets smaller, without suffering heavy loss in the rate of return, would attract investors. To extract only desired assets among all available assets, we need knowledge that identifies investors' preference for the risk of the assets. This study suggests two-layer decision-making rules capable of identifying an investor's risk preference and an architecture applying them to a quantitative portfolio model based on risk and expected return. Our knowledge-based portfolio system is to build an investor's preference-oriented portfolio. The empirical tests using the data from Korean capital markets show the results that our model contributes significantly to the construction of a better portfolio in the perspective of an investor's benefit/cost ratio than that produced by the existing portfolio models.

• Korean Management Science Review
• /
• v.32 no.1
• /
• pp.15-33
• /
• 2015

Under complete information, introducing additional constraints to a portfolio will have a negative impact on performance. However, real-life investments inevitably involve use of error-prone estimations, such as expected stock returns. In addition to the reality of incomplete data, investments of most Korean domestic equity funds are regulated externally by the government, as well as internally, resulting in limited maximum investment allocation to single stocks and risk free assets. This paper presents an investment framework, which takes such real-life situations into account, based on a newly developed portfolio selection model considering realistic constraints under incomplete information. Additionally, we examined the effects of additional constraints on portfolio's performance under incomplete information, taking the well-known Samsung and SK group stocks as performance benchmarks during the period beginning from the launch of each commercial fund, 2005 and 2007 respectively, up to 2013. The empirical study shows that an investment model, built under incomplete information with additional constraints, outperformed a model built without any constraints, and benchmarks, in terms of rate of return, standard deviation of returns, and Sharpe ratio.

• Asian Journal of Business Environment
• /
• v.7 no.4
• /
• pp.17-25
• /
• 2017

Purpose - The purpose of this study is to present a framework for determining the most appropriate business model for e-learning. Research design, data, and methodology - The Electronics Branch of Azad University has been elected as a case study in this research. This study conducted using a descriptive method. The information was obtained using interviews with experts including managers, faculty and students at the Electronics Branch of Azad University. Results - Three service-product system (product oriented system, use an oriented and result oriented system) approaches determined a framework for the formation of a portfolio. This portfolio is including three types of e-learning business models. Examining the relevant characteristics, correspondence of behaviorism learning theory with a product-oriented approach, correspondence of cognitivism theory with a user-oriented approach and in finally match correspondence of constructivist learning theory with a results-oriented approach which is evident. Conclusions - After reviewing the literature on the fields of e-learning, business model and product - service systems, we have achieved three types of e-learning business models. Then the variables in any of the business models were defined by using business model canvas tool and thus a portfolio consisting of three types of e-learning business model canvas was obtained.

• Journal of Korean Society for Quality Management
• /
• v.51 no.4
• /
• 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.

• Korean Management Science Review
• /
• v.26 no.2
• /
• pp.19-35
• /
• 2009

This paper investigated performance of the Markowitz's portfolio selection model with applications to Korean stock market. We chose Samsung-Group-Funds and KOSPI index for performance comparison with the Markowitz's portfolio selection model. For the most recent one and a half year period between March 2007 and September 2008, KOSPI index almost remained the same with only 0.1% change, Samsung-Group-Funds showed 20.54% return, and Markowitz's model, which is composed of the same 17 Samsung group stocks, achieved 52% return. We performed sensitivity analysis on the duration of financial data and the frequency of portfolio change in order to maximize the return of portfolio. In conclusion, according to our empirical research results with Samsung-Group-Funds, investment by Markowitz's model, which periodically changes portfolio by using nonlinear programming with only financial data, outperformed investment by the fund managers who possess rich experiences on stock trading and actively change portfolio by the minute-by-minute market news and business information.

• Venture DIGEST
• /
• s.92
• /
• pp.8-11
• /
• 2006

• Venture DIGEST
• /
• s.120
• /
• pp.8-11
• /
• 2008

• Venture DIGEST
• /
• s.116
• /
• pp.8-11
• /
• 2008

• Venture DIGEST
• /
• s.93
• /
• pp.8-11
• /
• 2006

• Venture DIGEST
• /
• s.117
• /
• pp.8-11
• /
• 2008