• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.04a
• /
• pp.314-317
• /
• 2000

금융파생상품인 옵션의 가치평가를 이해하는 데 널리 사용되는 이항분포모형은 다음과 같은 특징을 가지는 것으로 알려져 있다 첫째, 옵션의 가치는 주가의 상승 또는 하락할 확률과는 무관하게 결정된다. 둘째, 옵션의 가치는 투자자의 위험에 대한 태도와는 관계없이 결정된다. 이 논문에서는 옵션의 기초물인 주가가 한기간 후에 상승 또는 하락하는 기본모형에서 옵션의 가치평가가 주가의 변동 확률과 투자자의 위험에 대한 태도와 무관하지 않음을 예제를 통하여 밝히게 될 것이다.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.167-173
• /
• 2023

As research has been published to predict future data using regression analysis or artificial intelligence as a method of analyzing economic indicators. In this study, we designed a system that predicts prospective futures prices using artificial intelligence that utilizes topic probability data obtained from past news articles using topic modeling. Topic probability distribution data for each news article were obtained using the Latent Dirichlet Allocation (LDA) method that can extract the topic of a document from past news articles via unsupervised learning. Further, the topic probability distribution data were used as the input for a Long Short-Term Memory (LSTM) network, a derivative of Recurrent Neural Networks (RNN) in artificial intelligence, in order to predict prospective futures prices. The method proposed in this study was able to predict the trend of futures prices. Later, this method will also be able to predict the trend of prices for derivative products like options. However, because statistical errors occurred for certain data; further research is required to improve accuracy.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.291-300
• /
• 1999

본 논문은 인공신경망과 귀납적 학습방법 등의 인공지능 방법과 선물가격결정에 대한 기존 재무이론을 사용하여 일상어휘로 표현되는 파생상품 가격예측 모형을 개발하는데 있다. 모형의 개발은 1단계로 인공신경망이나 기존의 선물가격결정이론(평균보유비용모형이나 일반균형모형)을 이용하여 선물 가격을 예측한 후, 서로 비교분석하여 인공신경망 모형의 우수성을 확인하였다. 귀납적 학습방법중 CART 알고리듬을 사용하여 If-Then 규칙을 생성하였다. 특히 실용적 측면에서 선물가격의 일상어휘화를 통한 모형개발을 여러 가지 방법으로 시도하였다. 이러한 선물가격 예측모형의 유용성은 일단 If-Then 규칙으로 표현되어 전문가의 판단에 확실한 이론적인 근거를 제시할 수 있는 장점이 있으며, 특히 의사결정지원시스템으로 활용화 될 경우 매우 유용한 근거자료로 활용될 수 있다. 이러한 선물가격 예측모형은 정확성은 분석표본과 검증표본으로 나누어 검증표본에서 세가지 기본모형(평균보유비용모형, 일반균형모형, 인공신경망 모형)과 각 모형의 귀납적 학습방법 모형의 다른 3가지 어휘표현방법 3가지를 모형별로 비교 분석하였다. 분석결과 인공신경망모형은 상당한 예측력을 갖고 있는 것으로 판명되었으며, 특히 CART를 기반으로 한 일상어휘 기반의 선물가격예측 모형은 예측력이 높은 것으로 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.436-438
• /
• 2017

자본주의의 꽃인 주식시장은 파생시장에 의해 영향을 받고 있으며, 파생시장은 지수옵션 상품에 의해 영향을 받고 있다. 최근 들어 시스템 트레이딩에 대한 관심이 점점 더해가고 있으며 투자자에게 컴퓨터 시스템과 매매 전략에 대한 이해를 요구하고 있다. 지수옵션 시장은 만기일을 기준으로 마치 파도와 같이 순간순간 살아 움직이고 있다. 옵션에 대한 효과적인 관점은 투자자에게 확률 높은 매력적인 전략을 제공하며 옵션의 움직임을 전체적으로 해석할 수 있게 한다, 그리고 궁극적으로 옵션가의 예측을 가능하게 한다. 행사가와 방향성에 의한 개별 옵션은 함수로 해석될 수 있다. 다양한 입력값에 의해 가격이라는 하나의 출력값이 결정되는 구조이다. 입력값에는 지수, 시간, 거래량 의 세가지 카테고리로 이루어진다. 이중 거래량은 예측이 가능한데, 개별 옵션이 아닌 앙상불의 경우 출력값으로 처리될 수 있다. 하지만 앙상불 옵션에서 개별 옵션가는 경직성을 가지게 되어 예상가의 차이에 의한 압력이 발생하게 된다. 이 압력은 이후의 지수변화에 핵심적인 에너지로 작용할 수 있다. 압력의 측정은 다양한 방법이 있을 수 있는데, 본 논문에서는 뉴로-퍼지 시스템을 이용한 예측값과의 차이를 측정하여 계산하였다. 일단 학습된 뉴로-퍼지 시스템은 가격을 예측하게 되며, 실제 가격과의 괴리는 압력으로 해석할 수 있다.

• Environmental and Resource Economics Review
• /
• v.14 no.4
• /
• pp.943-964
• /
• 2005

This study estimated a wide range of stochastic process models using the frameworks of CKLS (1992) and Nowman and Wang (2001). For empirical analysis, the GMM estimation procedure is adopted for the monthly Brent crude oil prices from January 1996 to January 2005. Using the simulated price series, European call option premiums were calculated and compared each other. The empirical results suggest that the crude oil price has a strong dependency of volatility on the price level. Contrary to the results of previous related studies, it shows a weak tendency of mean reversion. In addition, the models provide different implications for pricing derivatives on crude oil.

• Environmental and Resource Economics Review
• /
• v.13 no.3
• /
• pp.417-440
• /
• 2004

For the behavior of the wholesale spot price, a regime switching model with time-varying transition probabilities was estimated using the data from the PJM (Pennsylvania-New Jersey-Maryland) market. By including the temperature as an explanatory variable in the transition probability equations, the threshold effect of changing regime is clearly enhanced. And hence the predictability of the price spikes was improved. This means that the model showed a very clear threshold effect, with a low probability of switching for low loads and low temperatures and a high probability for high loads and high temperatures. And temperature showed a clearer threshold effect than load does. This implies that weather-related contracts may help to hedge against the risk in the cost of buying electricity during a summer.

• Management & Information Systems Review
• /
• v.35 no.1
• /
• pp.273-286
• /
• 2016

This study investigated the information contents of KOSPI200 Options for intraday big market movement by using minute by minute data. The major findings are summarized as follows; First, big market movement occurred more frequently during 9:00~10:00 and 14:00~14:50. These phenomena reflect market unstability just after opening and near closing. Second, VKSOPI is most closely associated with extreme changes such as KOSPI200 jumps. Third, VKOSPI is showed more predictive power with negative KOSPI200 jumps than KOSPI200 jumps. Fourth, VKOSPI showed predictive power for the positive and negative jumps up to 30 minutes before the jumps occurs. The purpose of this study is to explore the most recent topics in the field of finance, research on market microstructure. This study is an important contribution to investigate intraday information comprehensively in terms of market microstructure effects using the 15-year long-term and the high-frequency data(minute by minute). The results of this study are expected to contribute to detect intraday true jumps, proactive development of market risk indicators, risk management, derivatives investment strategy.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.10
• /
• pp.4359-4368
• /
• 2011

Among several macroeconomic missteps blamed for the recent global financial crisis including the social problems of income distribution and the lack of proper financial remedies, two of them have received particular attention: the global BOP(Balance of Payment) imbalance and the misguided monetary policy. Such BOP imbalance was blamed for massive foreign exchange investment flows from Asia into the U.S., triggering the financial and real estate bubble in America. The latter refers to the excessively loose monetary policy of the U.S. Federal Reserve, which pushed financial institutions and households into reckless investment behavior in search of higher returns. Given the abuse of certain innovative financial techniques and new investment instruments that have been created in recent decades, both collateralized debt obligations (CDOs) and credit default swaps (CDS) enjoyed a symbiotic and toxic relationship prior to the financial crisis This paper is organized as follows: The first section analyzes the real causes of the recent financial crisis. The second details the role of CDOs and CDS. Then, to identify key determinants of the CDS spreads in an emerging capital market, the sample data of major Korean firms' CDS spreads are used to estimate the risk premium by utilizing the multiple regression analysis. The empirical test result indicates that Korean 3-year treasury bond rate(TYIELD), market to book value ratio(MV/BV), and assets size(INASSETS) are shown to demonstrate statistically significant influences on the changes of the CDS premium for sample firms.

• THE INTERNATIONAL COMMERCE & LAW REVIEW
• /
• v.55
• /
• pp.185-208
• /
• 2012

Before and after the Capital Market Integration Act in 2007 is implemented in South Korea, many of small-and mid sized exporting companies in South Korea has been bankrupted or filed for lawsuit claiming mis-selling(KIKO) by the banks. The basic economic structure of KIKO in Korea are part of a business model based on the use or misuse of exotic derivatives whose results are anything but imaginary. 571 mid sized exporting companies have been damaged about $28 billion. KIKO is a currency option product that sells foreign currencies at higher foreign exchange rate when the rate moves within a certain range, but sells foreign currencies at two or three times lower rate than the market price when the rate exceeds the designated upper limit. KIKO, Therefore, is hard to know whether the non financial firms intended to hedge against further strengthening of their currency or merely to speculate. It is also hard to know how thoroughly they understood the risk-return profile of these transactions. It is similarly hard to ascertain whether the derivatives dealers offering these transactions were meeting the demands of their clients or taking advantage of them. These exotic derivatives were inappropriate for either hedging or speculating, and no knowledgeable investor would be likely to enter into these contracts intentionally.

• Journal of Digital Contents Society
• /
• v.7 no.3
• /
• pp.211-217
• /
• 2006

The digital contents industry has now become the most important industry in the 21st century. Among the various digital contents industries, the animation industry has emerged as a higher value-added culture contents business with a strong possibility of growth from the field of image and character to the copyright area. Yet, the overall market structure has not been consolidated except for a few successful projects because of the sharp decline in domestic animation and the upward trend in global animation business. Due to reduced investment in producing TV animations, OSMU is an essential alternative for the animation industry. In this research, we aim to analyze the development of the domestic animation industries by studying the actual condition of OSMU for broadcasting contents.