• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.191-209
• /
• 2022

This paper is a review of studies that focus on the prediction of a won/dollar exchange rate before and after the covid 19 pandemic. The Korea economy has an unprecedent situation starting from 2021 up till 2022 where the won/dollar exchange rate has exceeded 1,400 KRW, a first time since the global financial crisis in 2008. The US Federal Reserve has raised the interest rate up to 2.5% (2022.7) called a 'Big Step' and the Korea central bank has also raised the interested rate up to 2.5% (2022.8) accordingly. In the unpredictable economic situation, the prediction of the won/dollar exchange rate has become more important than ever. The authors separated the period from 2015.Jan to 2022.Aug into three periods and built a best fitted ARIMA/ARDL prediction model using the period 1. Finally using the best the fitted prediction model, we predicted the won/dollar exchange rate for each period. The conclusions of the study were that during Period 3, when the usual relationship between exchange rates and economic factors appears, the ARDL model reflecting the variable relationship is a better predictive model, and in Period 2 of the transitional period, which deviates from the typical pattern of exchange rate and economic factors, the SARIMA model, which reflects only historical exchange rate trends, was validated as a model with a better predictive performance.

• The Korean Journal of Financial Studies
• /
• v.2 no.2
• /
• pp.367-382
• /
• 1995

본 연구에서는 시장평균환율제가 시행된 시점인 1990년 3월 2일부터 1991년 12윌 31일까지의 국내 원/달러 외환시장을 대상으로 선도환가격의 미래 예측기능, 즉 미래의 현물환율에 대한_불편추정치로서의 선도환율의 역할을 실증적으로 검증하였다. 국내 시중은행에서 거래한 달러 대비 원화의 현물환율과 1개월 만기의 선도환율 자료를 사용한 실증분석결과에 의하면, 현물환율은 선도환이 예측한 방향과는 반대의 방향으로 움직이거나 예측한 수준에 크게 벗어나고 있다. 그러나, 외환시장에 큰 영향을 준 것으로 보여지는 동 서독 통합과 중동전쟁을 기준으로 분석대상기간을 두개의 하부기간으로 나누어 다시 추정한 결과에 의하면, 선도환가격이 미래 현물환율에 대한 불편추정치라는 가설을 기각하지 못하고 있다. 이러한 결과는 환율변화에 대한 확율분포가 시간경과에 따라 크게 변하고 있으며, 실증분석에서는 이러한 분포의 시간종속성을 반드시 고려하여야 한다는 것을 시사하고 있다. 또한, 다른 외국통화에 대한 실증분석에서는 나타나지 않는 결과로서, 이는 우리나라 외환시장의 특성을 반영하고 있는 것으로 해석된다. 시장평균환율제가 변동폭을 제한하고 있으며 분석대상 기간 동안은 환율변동이 비교적 안정적이기 때문에, 선도환가격의 결정도 비교적 안정적으로 이루어 질 수 있었다. 이와 같은 요인들에 의하여, 현물환율의 변동이 매우 심한 다른 외국통화에 비하여, 원화 환율의 경우에는 선도환가격은 만기시의 현물환율에 근접하는 경향을 보이게 된 것으로 보여진다.

• International Area Studies Review
• /
• v.21 no.2
• /
• pp.3-20
• /
• 2017

Traditional co-integration analysis method is known to be difficult to clearly determine the relationship between the cointegrated variables. This study utilizes a fractional cointegation method and a causal analysis of time and frequency domain among the exchange rates of Korea, China and Japan. The results show that even though traditional cointegration methods did not clarify the existence of cointegration, exchange rates were fractionally cointegrated. Causal analysis of time domain and frequency domain provided somewhat different results, but the yen/dollar was useful for forecasting won/dollar and yuan/dollar. Proper use of causal analysis of frequency domain and fractional cointegration emthods may provide useful information that can not be explained from the traditional method.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.11
• /
• pp.71-79
• /
• 2017

In this paper, we implemented the exchange rate forecasting neural network using heterogeneous computing. Exchange rate forecasting requires a large amount of data. We used a neural network that could leverage this data accordingly. Neural networks are largely divided into two processes: learning and verification. Learning took advantage of the CPU. For verification, RTL written in Verilog HDL was run on FPGA. The structure of the neural network has four input neurons, four hidden neurons, and one output neuron. The input neurons used the US $ 1, Japanese 100 Yen, EU 1 Euro, and UK £ 1. The input neurons predicted a Canadian dollar value of $ 1. The order of predicting the exchange rate is input, normalization, fixed-point conversion, neural network forward, floating-point conversion, denormalization, and outputting. As a result of forecasting the exchange rate in November 2016, there was an error amount between 0.9 won and 9.13 won. If we increase the number of neurons by adding data other than the exchange rate, it is expected that more precise exchange rate prediction will be possible.

• The Korean Journal of Financial Studies
• /
• v.12 no.1
• /
• pp.183-213
• /
• 2006

본 연구의 목적은 공적분 검정과 예측오차 분산분해 방법을 이용하여 우리나라 주식시장에서 주가지수와 거시경제 변수들과의 계량적 관계를 파악하고 종합주가지수와 밀접한 관련성이 있는 변수를 사용하여 종합주가지수와 거시경제변수들 사이의 모형을 추정하는 것이다. Johansen 공적분 검증을 이용한 결과를 보면 종합주가지수와 7개의 거시경제변수들(총통화, 소비자물가지수, 금리, 산업생산지수, 원 달러 환율, 국제원유가격, 경상수지) 사이에 상당히 밀접한 연관성이 있으며, 이들 변수들 사이에 장기적 균형 관계가 존재하였다. 예측오차 분산분해 방법을 사용한 분석결과에서는 종합주가지수의 분산을 예측하는데 있어서 이들 거시경제변수들의 설명력이 매우 높게 나타났다. 또한 우리나라의 주식시장에서는 금리, 국제원유가격, 경상수지 등의 요인보다는 원 달러 환율, 소비자물가지수, 산업생산의 비중이 더 크다는 사실을 알 수 있었다. 우리나라의 자본시장에서는 1997년 말 외환위기를 전후로 하여 현저한 구조적 변화가 존재하였기 때문에 백터오차수정모형을 설정할 때에는 외환위기 이전기간과 이후기간으로 나누어서 분석하는 것이 더욱 타당함을 확인할 수 있었다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.5
• /
• pp.1043-1051
• /
• 2009

This study intends to discuss the influence on behaviors of won/dollar exchange rate after a FTA between Korea and US come into effect. The change of behaviors of won/dollar exchange rate has been looked into concerning other countries who have signed a FTA pact with the US, and these examples were compared with that of Korea so as to find similarities and differences. As a result of analyses, behaviors of exchange rate between FTA-pact countries were showed differently. Volatility and risk premium somewhat decreased after the FTA took effect except for Chile. As for Chile, showing intense volatility, foreign exchange risk premium rather increased. It can be concluded that the relationship between volatility and risk premium of individual exchange rate is established and FTA can influence change of these behaviors of exchange rate depending on the situation of individual country. This study will contribute to offer informations to Korea trading companies related to IT that will have to prepare for the uncertainties of change of exchange rate due to FTA between Korea and US.

• The Korean Journal of Applied Statistics
• /
• v.26 no.1
• /
• pp.1-14
• /
• 2013

ARIMA and ARIMA+IGARCH models are fitted and compared for daily Korean won/US dollar exchange rate data over 17 years. A linear structural change model and an autoregressive structural change model are fitted for multiple change-point estimation since there seems to be structural change with this data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.5
• /
• pp.229-235
• /
• 2012

Forex trading participants, due to the intensified economic internationalization exchange risk avoidance measures are needed. In this research, Model suitable for estimation of time-series data, such as stock prices and exchange rates, through the concealment of HMM and estimate the short-term exchange rate forecasting model is applied to the prediction of the future. Estimated by applying the optimal model if the real exchange rate data for a certain period of the future will be able to predict the movement aspect of it. Alleged concealment of HMM. For the estimation of the model to accurately estimate the number of states of the model via Bayesian Information Criterion was confirmed as a model predictive aspect of physical exercise aspect and predict the movement of the two curves were similar.

• The Korean Journal of Applied Statistics
• /
• v.33 no.3
• /
• pp.257-267
• /
• 2020

We introduce multivariate exponential smoothing models based on a vector innovations structural time series framework. The models enable us to exploit potential inter-series dependencies to improve the fit and forecasts of multivariate (vector) time series. Models are applied to forecast the exchange rates of the UK pound (UKP) and US dollar (USD) against the Korean won (KRW) observed on monthly basis; subseqently, we compare their performance with alternative models. We observe that the multivariate exponential smoothing models are superior to alternatives.

• The Korean Journal of Applied Statistics
• /
• v.24 no.6
• /
• pp.1033-1043
• /
• 2011

In this paper, we use a nested family of models of Generalized Autoregressive Conditional Heteroscedasticity(GARCH) to verify asymmetric conditional heteroscedasticity in the KOSPI and Won-Dollar exchange rate. This study starts from an investigation of whether time series data have asymmetric features not explained by standard GARCH models. First, we use kernel density plot to show the non-normality and asymmetry in data as well as to capture asymmetric conditional heteroscedasticity. Later, we use three representative asymmetric heteroscedastic models, EGARCH(Exponential Garch), GJR-GARCH(Glosten, Jagannathan and Runkle), APARCH(Asymmetric Power Arch) that are improved from standard GARCH models to give a better explanation of asymmetry. Thereby we highlight the fact that volatility tends to respond asymmetrically according to positive and/or negative values of past changes referred to as the leverage effect. Furthermore, it is verified that how the direction of asymmetry is different depending on characteristics of time series data. For the KOSPI and Korean won-US dollar exchange rate, asymmetric heteroscedastic model analysis successfully reveal the leverage effect. We obtained predictive values of conditional volatility and its prediction standard errors by using moving block bootstrap.