• Korean Management Science Review
• /
• v.29 no.2
• /
• pp.53-64
• /
• 2012

This paper is about the investment strategy in stocks on Fundamental analysis. Financial data of stocks from January 2. 2001 through October 30. 2009 were utilized in order to suggest the investment strategies. Fundamental analysis was used in stocks-related strategy. The portfolios are composed of 3 criteria such as the buying criteria score, exchange cycle and selling conditions. The buying criteria score is determined assigned to each stock index according to the satisfaction condition of 15 parameters selected considering the grue's criteria. The stock buying alternatives has two options with buying stocks over 13 points and over 14 points of buying criteria score. The seven exchange cycles and three selling methods are considered. So total number of portfolios is 42($2{\times}7{\times}3=42$). The simulation has been executed about each 42 portfolios and we figured out with the simulation result that 83.33% of 35 portfolios are more profitable than average stock market profit(203.43%). The outcome of this research is summarized in two parts. First, it's the exchange strategy of portfolio. The result shows that value-oriented investment (long-term investment) strategy yields much higher than short-term investment strategies of stocks. Second, it's about the exchange cycle forming the portfolios. The result shows that the rate of return for the portfolio is the best when exchange cycle is 18 months.

• Journal of Intelligence and Information Systems
• /
• v.1 no.2
• /
• pp.103-121
• /
• 1995

This study proposes a artificial neural network method to predict the time to buy and sell the stocks listed on the Korea Composite Stock Price Index(KOSPI). Four types (NN1, NN2, NN3, NN4) of independent networks were developed to predict KOSPIs up/down direction after four weeks. These networks have a difference only in the length of learning period. NN5 - arithmetic average of four networks outputs - shows an higher accuracy than other network types and Multiple Linear Regression (MLR), and buying and selling simulation using systems outputs produces higher reture than buy-and-hold strategy.

• The Journal of the Korea Contents Association
• /
• v.12 no.2
• /
• pp.472-482
• /
• 2012

There are many investors in the stock market, and more and more people get interested in the stock investment. In order to avoid risks and make profit in the stock investment, we have to determine several aspects using various information. That is, we have to select profitable stocks and determine appropriate buying/selling prices and holding period. This paper proposes a data mining tool for the investors' decision support. The data mining tool makes stock investors apply machine learning techniques and generate stock price prediction model. Also it helps determine buying/selling prices and holding period. It supports individual investor's own decision making using past data. Using the proposed tool, users can manage stock data, generate their own stock price prediction models, and establish trading policy via investment simulation. Users can select technical indicators which they think affect future stock price. Then they can generate stock price prediction models using the indicators and test the models. They also perform investment simulation using proper models to find appropriate trading policy consisting of buying/selling prices and holding period. Using the proposed data mining tool, stock investors can expect more profit with the help of stock price prediction model and trading policy validated on past data, instead of with an emotional decision.