• 응용통계연구
• /
• 제29권3호
• /
• pp.505-512
• /
• 2016

본 연구에서는 금융시계열의 일간 변동성 측정을 위해 가중 융합 방법을 제안하고 있다. 고빈도(high frequency)자료에 기반을 둔 조정된 실현변동성을 계산하고 이를 참 값으로 간주하여 제안된 가중 융합 변동성에서 최적 가중치를 결정하는 과정을 서술하였다. 국내 KOSPI200자료의 1분 단위 고빈도 주가로부터 조정된 실현변동성을 구한 후 최적의 가중 융합 변동성을 제안해 보았다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.313-317
• /
• 2001

The approach to predict time series without neglecting the fluctuation in a short period is tried by using a digital FIR filter and a neural network. The differential waveform of the Nikkei average closing price is filtered by the FIR band-pass filter of 101 length. It is filtered into the five frequency bands of 0-1Hz, 1-2Hz, 2-3Hz, 3-4Hz and 4-5Hz by setting the sampling frequency 10Hz. The each filtered waveform is learned and forecasted by the neural network. The neural network of the back propagation method is adopted in the learning the waveform. By inputting the data of 20 days in the past, the prediction of 10 days ahead is carried out. After learning the time series of each frequency band by the neural network, the predicted data far each frequency band are obtained. The predicted waveforms of each frequency band are synthesized to obtain a final forecast. The waveform can be forecasted well as a whole.

• 유통과학연구
• /
• 제16권9호
• /
• pp.53-58
• /
• 2018

Purpose - This study aims to examine how the time variations of customer satisfaction influence retail firms' performance. Research design, data, and methodology - The study employs yearly time series customer satisfaction data of Korean retail secured from the National Customer Satisfaction Index(NCSI) for the 2011~2016 period. Our data includes a total of 90 observations of 15 retail firms in 5 different sector(department store, filling station, large discount store, open market, TV home shopping). We obtained the firm performance data from the KIS Value database. The variables for financial performance include sales and net profit. Results - The results show that customer satisfaction has dynamic effects on retail firms' performance. More specifically, the time variation of customer satisfaction has the moderating effect on the linkage between customer satisfaction and financial performance as well as direct effects on the firms' financial performance. Conclusions - Customer satisfaction has the current effect lasting over time on firm performance and changes of customer satisfaction in positive direction also impact on firm performance. Retail firms need to not only focus on improving customer satisfaction in the current term, but make efforts to continuously enhance customer satisfaction in the long term.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권10호
• /
• pp.531-541
• /
• 2020

This study aims to determine the nature of the association between dividend policy and a corporation's financial performance in emerging countries, as well as the main variables that may have an effect on financial performance. The study included 92 industrial and service sector companies listed on the Amman Stock Exchange (ASE) during the period from 2015 to 2019. The study used Panel Data Analysis and cross-sectional time-series data and simple and multiple linear regression models. A multiple regression model was also developed in order to test whether guess factors may have a possible impact on financial performance (such as Dividend Yield, Dividend Pay-out Ratio, Firm Size, Leverage Ratio, Current Ratio). The data was collected from the annual reports and information that was available on the ASE website covering the period from 2015 to 2019. The results detect a strong relation between DY, DPR, and FSIZE variables that explain firm performance. Also leverage ratio is negatively and significantly associated with ROA and AOE. Moreover, no relations were detected between current ratio and financial performance. The study's conclusion is that dividend policy explains a lot of a company's financial performance, meaning that the dividend policy has a statistically significant impact on company financial performance.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권11호
• /
• pp.21-29
• /
• 2021

The objective of this study is to see how a country's level of democracy impacts the relationship between financial development and income disparity. We argue that political regimes, supported by their degree of democracy, are important for various decentralization theories to predict the impact of financial development on income inequality. Our study tests this argument using Vietnam time series data for the period 2000-2020 through the ARDL model. The financial development variable is represented by five proxies, the income inequality variable is represented by the GINI coefficient and the role of democracy is represented by the Freedom House Index. Data serving for the study is taken from data sources with high reliability. The results of the study have strong evidence that (1) financial development has a positive impact on income inequality, (2) democratic government will reduce national income inequality. (3) And a higher degree of democracy tends to mitigate the positive impact of financial development on income inequality. Thus, our study contributes to the literature by providing a new look at the mixed results regarding the relationship between financial development and theoretical income inequality. Finally, the article provides policy implications for the Government of Vietnam.

• 응용통계연구
• /
• 제26권5호
• /
• pp.785-796
• /
• 2013

News impact curves(NIC)는 1993년 Engle와 Ng에 의하여 제시되었으며, 이는 시계열 자료에서 발생하는 변동성을 시각적으로 나타내는데 용이하다. 본 논문에서는 기존의 NIC에서 더 나아가, 2차원 NIC(two dimensional NIC)와 주성분 NIC(PCA in NIC)를 제안하였으며, KOSDAQ 자료에서 적용하여 보았다.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권6호
• /
• pp.109-116
• /
• 2020

The study examines the nexus between financial development and economic growth in India during Q1: 1996 to Q3: 2018. This study employs time-series data of real GDP and ratio of broad money to GDP as a proxy for economic and financial development, respectively. The data are obtained from RBI database on the Indian economy. All variables are seasonally adjusted using X12-arima technique and expressed in natural logarithm form. Non-linear Autoregressive Distributed Lag (NARDL) bound test has been used to check for cointegrating relationship of these two variables. Empirical findings suggest that, unlike in the short run, in the long run financial development does impact economic growth positively. Further, a symmetric effect of positive and negative components of financial development is found for the Indian economy, whereas the effect of control variable like exchange rate and trade openness is in consonance with common economic intuition. Exchange rate is in consonance with intuitive economic logic that a fall in exchange rate makes exports cheaper and increases the quantity of export, which improves the balance of payment and leads to a rise in aggregate demand, hence improves economic growth. This paper contributes to the existing literature on India by breaking down financial indicator into positive and negative components to examine the finance-growth relationship.

• 응용통계연구
• /
• 제30권6호
• /
• pp.983-991
• /
• 2017

본 논문은 고빈도 시계열 자료 분석을 위한 최신 함수-변동성 functional ARCH : fARCH(1) 모형을 독자들에게 소개하고 국내 자료 적합을 예시하고 있다. fARCH(1) 모형을 KOSPI/현대차 1분 단위 고빈도 수익률 자료에 적합하여 기존의 ARCH 모형에서는 할 수 없었던 다이나믹한 일중(intraday) 변동성을 추정할 수 있음을 보여주고 있다.

• 품질경영학회지
• /
• 제50권3호
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• 지능정보연구
• /
• 제23권3호
• /
• pp.139-153
• /
• 2017

기업의 부도는 이해관계자들뿐 아니라 사회에도 경제적으로 큰 손실을 야기한다. 따라서 기업부도예측은 경영학 연구에 있어 중요한 연구주제 중 하나로 다뤄져 왔다. 기존의 연구에서는 부도 예측을 위해 다변량판별분석, 로짓분석, 신경망분석 등 다양한 방법론을 이용하여 모형의 부도 예측력을 높이고 과적합의 문제를 해결하고자 시도하였다. 하지만 기존의 연구들이 시간적 요소를 고려하지 않아 발생할 수 있는 문제점들을 갖고 있음에도 불구하고 부도 예측에 있어서 동적 모형을 이용한 연구는 활발히 진행되고 있지 않으며 따라서 동적 모형을 이용하여 부도예측모형이 더욱 개선될 여지가 있다는 점을 확인할 수 있었다. 이에 본 연구에서는 RNN(Recurrent Neural Network)을 이용하여 시계열 재무 데이터의 동적 변화를 반영한 모형을 만들었으며 기존의 부도예측모형들과의 비교분석을 통해 부도 예측력의 향상에 도움이 된다는 것을 확인할 수 있었다. 모형의 유용성을 검증하기 위해 KIS Value의 재무 데이터를 이용하여 실험을 수행하였고 비교모형으로는 다변량판별분석, 로짓분석, SVM, 인공신경망을 선정하였다. 실험 결과 제안된 모형이 비교 모형에 비해 우수한 예측력을 보이는 것으로 나타났다. 따라서 본 연구는 변수들의 변화를 포착하는 동적 모형을 부도예측에 새롭게 제안하여 부도예측 연구의 발전에 기여할 수 있을 것으로 기대된다.