• Asia pacific journal of information systems
• /
• 제11권4호
• /
• pp.99-111
• /
• 2001

The prediction of stock price index is a very difficult problem because of the complexity of stock market data. It has been studied by a number of researchers since they strongly affect other economic and financial parameters. The movement of stock price index has a series of change points due to the strategies of institutional investors. This study presents a two-stage forecasting model of stock price index using change-point detection and artificial neural networks. The basic concept of this proposed model is to obtain intervals divided by change points, to identify them as change-point groups, and to use them in stock price index forecasting. First, the proposed model tries to detect successive change points in stock price index. Then, the model forecasts the change-point group with the backpropagation neural network(BPN). Finally, the model forecasts the output with BPN. This study then examines the predictability of the integrated neural network model for stock price index forecasting using change-point detection.

• 한국정보통신학회논문지
• /
• 제25권10호
• /
• pp.1435-1440
• /
• 2021

저금리 시대의 도래로 인해 많은 투자자들이 주식 시장으로 몰리고 있다. 과거의 주식 시장은 사람들이 기업 분석 및 각자의 투자기법을 통해 노동 집약적으로 주식 투자가 이루어졌다면 최근 들어 인공지능 및 데이터를 활용하여 주식 투자가 널리 이용되고 있는 실정이다. 인공지능을 통해 주식 예측의 성공률은 현재 높지 않아 다양한 인공지능 모델을 통해 주식 예측률을 높이는 시도를 하고 있다. 본 연구에서는 다양한 인공지능 모델에 대해 살펴보고 각 모델들간의 장단점 및 예측률을 파악하고자 한다. 이를 위해, 본 연구에서는 주식예측 인공지능 프로그램으로 인공신경망(ANN), 심층 학습 또는 딥 러닝(DNN), k-최근접 이웃 알고리즘(k-NN), 합성곱 신경망(CNN), 순환 신경망(RNN), LSTM에 대해 살펴보고자 한다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 추계정기학술대회:지능형기술과 CRM
• /
• pp.427-436
• /
• 2000

The prediction of stock price index is a very difficult problem because of the complexity of the stock market data it data. It has been studied by a number of researchers since they strong1y affect other economic and financial parameters. The movement of stock price index has a series of change points due to the strategies of institutional investors. This study presents a two-stage forecasting model of stock price index using change-point detection and artificial neural networks. The basic concept of this proposed model is to obtain Intervals divided by change points, to identify them as change-point groups, and to use them in stock price index forecasting. First, the proposed model tries to detect successive change points in stock price index. Then, the model forecasts the change-point group with the backpropagation neural network (BPN). Fina1ly, the model forecasts the output with BPN. This study then examines the predictability of the integrated neural network model for stock price index forecasting using change-point detection.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1997년도 추계학술대회발표논문집; 홍익대학교, 서울; 1 Nov. 1997
• /
• pp.105-108
• /
• 1997

Previous studies in stock market predictions using artificial intelligence techniques such as artificial neural networks and case-based reasoning, have focused mainly on spot market prediction. Korea launched trading in index futures market (KOSPI 200) on May 3, 1996, then more people became attracted to this market. Thus, this research intends to predict the daily up/down fluctuant direction of the price for KOSPI 200 index futures to meet this recent surge of interest. The forecasting methodologies employed in this research are the integration of genetic algorithm and artificial neural network (GAANN) and the integration of genetic algorithm and case-based reasoning (GACBR). Genetic algorithm was mainly used to select relevant input variables. This study adopts the categorical data preprocessing based on expert's knowledge as well as traditional data preprocessing. The experimental results of each forecasting method with each data preprocessing method are compared and statistically tested. Artificial neural network and case-based reasoning methods with best performance are integrated. Out-of-the Model Integration and In-Model Integration are presented as the integration methodology. The research outcomes are as follows; First, genetic algorithms are useful and effective method to select input variables for Al techniques. Second, the results of the experiment with categorical data preprocessing significantly outperform that with traditional data preprocessing in forecasting up/down fluctuant direction of index futures price. Third, the integration of genetic algorithm and case-based reasoning (GACBR) outperforms the integration of genetic algorithm and artificial neural network (GAANN). Forth, the integration of genetic algorithm, case-based reasoning and artificial neural network (GAANN-GACBR, GACBRNN and GANNCBR) provide worse results than GACBR.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제3권10호
• /
• pp.441-450
• /
• 2014

주식시장은 항상 변하며 특별한 이유 없이도 주가가 급락하거나 급등하는 현상도 나타난다. 그러므로 주식시장은 복잡계로 인식되고 있으며, 주가의 변화는 예측하기 어렵다. 최근에 많은 연구자는 주식시장을 개별 주식 간의 네트워크로 간주하고 그것을 이해하려고 하며, 인터넷에서 실시간으로 생성되는 빅데이터를 통해 주가의 변화를 밝히려고 노력하고 있다. 우리는 주가와 인터넷 특히 주식토론방에 나타나는 사람들의 반응 간의 상관관계에 주목한다. 이 상관관계를 밝히기 위해서 KOSPI200에 속한 회사 중 57개 회사와 관련 있는 게시물들을 수집하고 분석하였다. 분석 결과에 따르면, 개별 주가와 게시물 수 사이에는 특별한 상관관계가 나타나지 않았지만, 주가와 게시물 수의 상관관계가 주식 수익률과 관계가 있는 것으로 나타났다. 우리는 이 분석결과를 기반으로 주식투자 포트폴리오를 추천하는 새로운 방법을 제안한다. '다음' 포털의 주식토론방 데이터를 이용한 모의 투자 실험 결과에서, '다음' 주식토론방 데이터를 사용한 경우 제안 방법으로 구성한 주식 포트폴리오의 월평균 수익률은 약 1.55%로 마코위츠의 효율적 포트폴리오의 수익률보다 약 0.72% 높으며, 코스피 평균 수익률보다 약 1.21% 높게 나타났다. 또한 '네이버' 주식토론방 데이터를 사용한 경우는 모의 투자 수익률이 약 0.90%로 기존 방법과 마코위츠 효율적 포트폴리오와 코스피 평균 수익률보다 각각 0.35%와 0.40%, 0.58% 높게 나타났다. 이 연구는 인터넷 주식토론방에 나타난 사람들의 집단적인 행위는 주식시장을 이해하는 데 많은 도움을 줄 수 있으며, 주가와 사람들의 집단행위 사이의 상관관계가 주식투자에 활용될 수 있음을 제시하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권1호
• /
• pp.7-12
• /
• 2003

In recent years, many attempts have been made to predict the behavior of bonds, currencies, stock or other economic markets. Most previous experiments used the neural network models for the stock market forecasting. The KOSPI 200 (Korea Composite Stock Price Index 200) is modeled by using different neural networks and fuzzy logic. In this paper, the neural network, the dynamic polynomial neural network (DPNN) and the fuzzy logic employed for the prediction of the KOSPI 200. The prediction results are compared by the root mean squared error (RMSE) and scatter plot, respectively. The results show that the performance of the fuzzy system is little bit worse than that of the DPNN but better than that of the neural network. We can develop the desired fuzzy system by optimization methods.

• 지능정보연구
• /
• 제2권2호
• /
• pp.43-54
• /
• 1996

Financial markets are operating 24 hours a day throughout the world and interrelated in increasingly complex ways. Telecommunications and computer networks tie together markets in the from of electronic entities. Financial practitioners are inundated with an ever larger stream of data, produced by the rise of sophisticated database technologies, on the rising number of market instruments. As conventional analytic techniques reach their limit in recognizing data patterns, financial firms and institutions find neural network techniques to solve this complex task. Neural networks have found an important niche in financial a, pp.ications. We a, pp.y neural networks to Standard and Poor's (S&P) 500 stock index futures trading to predict the futures marker behavior. The results through experiments with a commercial neural, network software do su, pp.rt future use of neural networks in S&P 500 stock index futures trading.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.274-284
• /
• 2022

By explaining the essence of corporate governance as well as disclosure and transparency, the study examined the guarantees of applying disclosure and transparency to firms listed on the Saudi stock exchange. The research also addressed the disclosure and transparency duties of firms listed on the Saudi stock exchange. Finance to prepare a prospectus, as the Capital Market Authority's regulations required that the prospectus includes information that enables the investor in securities to make his investment decision based on real foundations based on the issuing company's financial position and to ensure that companies fulfill that disclosure in the prospectus. Firms who fail to disclose are required by law to do so, and the Capital Market Authority's laws mandate companies listed on the financial market to regularly report fundamental events linked to the issuer or the securities issued by it. The Capital Market Authority must make it available to the public dealing with the business issuing the securities, and The Capital Market Authority's Law and Regulations have imposed fines on corporations that do not comply with disclosure and make the Board of Director's report available. The research focused on activities that the legislator deemed to be a breach of the obligation of openness, such as the danger of many measures aimed at ensuring the impartiality and transparency of trading in the Saudi financial market, as well as the absence of conflicts of interest. The research also addressed the sanctions imposed on The source for failing to meet the obligation of disclosure and openness, as well as the mechanisms of compensating persons harmed by the failure to meet that responsibility.

• 한국경영과학회지
• /
• 제38권4호
• /
• pp.11-33
• /
• 2013

We analyzed the structures and properties of the global financial market networks using social network analysis approach. The Minimum Spanning Tree (MST) lengths and networks of the global financial markets based on the correlation coefficients have been analyzed. Firstly, similar to the previous studies on the global stock indices using MST length, the diversification effects in the global multi-asset portfolio can disappear during the crisis as the correlations among the asset class and within the asset class increase due to the system risks. Second, through the network visualization, we found the clustering of the asset class in the global financial markets network, which confirms the possible diversification effect in the global multi-asset portfolio. Meanwhile, we found the changes in the structure of the network during the crisis. For the last one, in terms of the degree centrality, the stock indices were the most influential to other assets in the global financial markets network, while in terms of the betweenness centrality, Gold, Silver and AUD. In the practical perspective, we propose the methods such as MST length and network visualization to monitor the change of the correlation risk for the risk management of the multi-asset portfolio.

• International Journal of Computer Science & Network Security
• /
• 제22권8호
• /
• pp.420-424
• /
• 2022

The Arab Automotive Company was the first corporation in Saudi Arabia and was founded in 1928. Since then, the number of Saudi corporations had increased. In 1985, Tadawul (The Saudi Stock Exchange ) was instituted under the supervision of the Saudi Arabian Monetary Authority (SAMA) and the base value of the index was 1000. This decision came as a response to accelerated growth in the number of Saudi corporations which had increased during the 1970s as the Saudi's economy developed.