• 산업경영시스템학회지
• /
• 제14권24호
• /
• pp.207-219
• /
• 1991

We studied performance evaluation methods for each cause by using a benchmark and also researched performance measurement models which based on CAPM. In this study, we analyzed the beneficiary certificate of stock type of three large domestic investment trust company. The purpose of this paper is improving the efficiency of investment maintenance and the operating the ability of fund operator by analyzing the contribution of the rate of return on investment and the cause of operating performance. We applied this study to the increasing aspect of stock price(Jan. 1988-April. 1999) as well as the decreasing aspect of stock price(April, 1989-July. 1990).

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 춘계정기학술대회
• /
• pp.399-408
• /
• 2001

This paper presents a simultaneous optimization approach of case-based reasoning (CBR) using a genetic algorithm(GA) for the prediction of stock price index. Prior research suggested many hybrid models of CBR and the GA for selecting a relevant feature subset or optimizing feature weights. Most studies, however, used the GA for improving only a part of architectural factors for the CBR system. However, the performance of CBR may be enhanced when these factors are simultaneously considered. In this study, the GA simultaneously optimizes multiple factors of the CBR system. Experimental results show that a GA approach to simultaneous optimization of CBR outperforms other conventional approaches for the prediction of stock price index.

• 지능정보연구
• /
• 제23권2호
• /
• pp.123-138
• /
• 2017

주식 시장은 거래자들의 기업과 시황에 대한 기대가 반영되어 움직이기에, 다양한 원천의 텍스트 데이터 분석을 통해 주가 움직임을 예측하려는 연구들이 진행되어 왔다. 주가의 움직임을 예측하는 것이기에 단순히 주가의 등락 뿐만이 아니라, 뉴스 기사나 소셜 미디어의 반응에 따라 거래를 하고 이에 따른 수익률을 분석하는 연구들이 진행되어 왔다. 주가의 움직임을 예측하는 연구들도 다른 분야의 텍스트 마이닝 접근 방안과 동일하게 단어-문서 매트릭스를 구성하여 분류 알고리즘에 적용하여 왔다. 문서에 많은 단어들이 포함되어 있기 때문에 모든 단어를 가지고 단어-문서 매트릭스를 만드는 것보다는 단어가 문서를 범주로 분류할 때 기여도가 높은 단어들을 선정하여야 한다. 단어의 빈도를 고려하여 너무 적은 등장 빈도나 중요도를 보이는 단어는 제거하게 된다. 단어가 문서를 정확하게 분류하는 데 기여하는 정도를 측정하여 기여도에 따라 사용할 단어를 선정하기도 한다. 단어-문서 매트릭스를 구성하는 기본적인 방안인 분석의 대상이 되는 모든 문서를 수집하여 분류에 영향력을 미치는 단어를 선정하여 사용하는 것이었다. 본 연구에서는 개별 종목에 대한 문서를 분석하여 종목별 등락에 모두 포함되는 단어를 중립 단어로 선정한다. 선정된 중립 단어 주변에 등장하는 단어들을 추출하여 단어-문서 매트릭스 생성에 활용한다. 중립 단어 자체는 주가 움직임과 연관관계가 적고, 중립 단어의 주변 단어가 주가 상승에 더 영향을 미칠 것이라는 생각에서 출발한다. 생성된 단어-문서 매트릭스를 가지고 주가의 등락 여부를 분류하는 알고리즘에 적용하게 된다. 본 연구에서는 종목 별로 중립 단어를 1차 선정하고, 선정된 단어 중에서 다른 종목에도 많이 포함되는 단어는 추가적으로 제외하는 방안을 활용하였다. 온라인 뉴스 포털을 통해 시가 총액 상위 10개 종목에 대한 4개월 간의 뉴스 기사를 수집하였다. 3개월간의 뉴스 기사를 학습 데이터로 분류 모형을 수립하였으며, 남은 1개월간의 뉴스 기사를 모형에 적용하여 다음 날의 주가 움직임을 예측하였다. 본 연구에서 제안하는 중립 단어 활용 알고리즘이 희소성에 기반한 단어 선정 방안에 비해 우수한 분류 성과를 보였다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1996년도 추계학술대회발표논문집; 고려대학교, 서울; 26 Oct. 1996
• /
• pp.207-210
• /
• 1996

Learning methodologies such as neural networks or genetic algorithms usually require long training times. Case based reasoning, however, attains peak performance swiftly and is often appropriate for learning even with small data sets. Previous work has shown that an extended case reasoning methodology can yield superior performance in the task of predicting financial data series. This paper examines the impact of reasoning procedures on stock price prediction. The following characteristics are evaluated: size of input vector, multiplicity of neighboring states, and a scaling factor for growth. The concepts are illustrated in the context of predicting the price of an individual price.

• Asia pacific journal of information systems
• /
• 제30권4호
• /
• pp.719-740
• /
• 2020

The stock market changes continuously as new information emerges, affecting the judgments of investors. Online news articles are valued as a traditional window to inform investors about various information that affects the stock market. This paper proposed new ways to utilize online news articles with technical indicators. The suggested hybrid model consists of three models. First, a self-attention-based convolutional neural network (CNN) model, considered to be better in interpreting the semantics of long texts, uses news content as inputs. Second, a self-attention-based, bi-long short-term memory (bi-LSTM) neural network model for short texts utilizes news titles as inputs. Third, a bi-LSTM model, considered to be better in analyzing context information and time-series models, uses 19 technical indicators as inputs. We used news articles from the previous day and technical indicators from the past seven days to predict the share price of the next day. An experiment was performed with Korean stock market data and news articles from 33 top companies over three years. Through this experiment, our proposed model showed better performance than previous approaches, which have mainly focused on news titles. This paper demonstrated that news titles and content should be treated in different ways for superior stock price prediction.

• The Journal of Asian Finance, Economics and Business
• /
• 제6권4호
• /
• pp.37-43
• /
• 2019

The research aims to study the relationship between export performance and stock return of Vietnamese fishery companies. To conduct this study, quarterly data was collected for period from 2010-2018 of 13 fishery companies listing in Ho Chi Minh Stock Exchange (HOSE) and Ha Noi Stock Exchange (HNX). The export performance was measured by export intensity, export growth and export market coverage. In addition, interest rate, exchange rate, GDP, firm size, profitability, and financial leverage were considered as the control variables in the research model. Panel data analysis with Generalized Least Squares model was employed to estimate the predictive regression. The findings indicated that export intensity and export growth have a significant and positive relationship with stock returns. However, export market coverage has not a significant relationship with stock return at the 0.05 level. Profitability, financial leverage, and exchange rate have a positive relationship, while interest rate and GDP have no relation to stock return at the 0.05 significance level. The findings imply that investors should consider the export intensity instead of export growth and export market coverage as selecting stock of fishery exports firms to invest; managers should increase export intensity to increase company's stock price or firm market value.

• 한국융합학회논문지
• /
• 제10권1호
• /
• pp.7-12
• /
• 2019

신경회로망은 적합한 수학적 모델에 대한 가정 없이 데이터로부터 유용한 정보를 추출해서 예측에 필요한 입출력 관계를 정의할 수 있어서 주가 예측에 널리 사용되어 왔다. 본 논문에서는 신경회로망 모델을 사용하여 일별 KOrea composite Stock Price Index (KOSPI) 종가를 예측한다. 예측된 종가를 기반으로 KOSPI에 연동해 변동하는 Exchange Traded Funds (ETFs)의 거래를 위한 알파 매매를 제안한다. 본 논문에 제안된 방법으로 KOSPI 예측 신경회로망 모델들을 구현하고 예측 정확도를 평가한다. 구현된 신경회로망 모델(NN1)의 학습 오차(MAPE)는 0.427, 평가 오차는 0.627이다. 평가용 데이터를 사용해 알파 매매를 시뮬레이션하면 수익률은 7.16 ~ 15.29 %를 보인다. 이는 125 거래일 데이터로 거둔 수익률로 제안된 알파 매매가 효과적임을 보인다.

• The Journal of Asian Finance, Economics and Business
• /
• 제1권3호
• /
• pp.29-36
• /
• 2014

This paper attempts to measure the impact of non-financial factors including analyst practices and broker resources on performance of sell side research. Results reveal that these non-financial factors have a measurable impact on performance of target price forecasts. Number of pages written by an analyst (surrogate for analyst practice) is significantly and directly linked with target price accuracy indicating a more elaborate analyst produces better target price forecasts. Analyst compensation (surrogate for broker resource) is significantly and inversely linked with target price accuracy. Out performance by analysts working with lower paying firms is possibly associated with motivation to migrate to higher paying broking firms. The study finds that employing more number of analysts per research report has no significant impact on target price accuracy -negative coefficient indicates that team work may not result in better target price forecasts. Though insignificant, long term forecast horizon negatively affects target price accuracy while stock volatility improves target price accuracy.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1996년도 춘계공동학술대회논문집; 공군사관학교, 청주; 26-27 Apr. 1996
• /
• pp.745-748
• /
• 1996

Korea Composite Stock Price Index (KOSPI) was predicted using Cascade Correlation Network (CCN) model. CCN was suggested, by Fahlman and Lebiere [1990], to overcome the limitations of backpropagation algorithm such as step size problem and moving target problem. To test the applicability of CCN as a function approximator to the stock price movements, CCN was used as a tool for univariate time series analysis. The fitting and forecasting performance fo CCN on the KOSPI was compared with those of Multi-Layer Perceptron (MLP).

• 재무관리연구
• /
• 제11권2호
• /
• pp.175-193
• /
• 1994

This paper relates the valuation consequences of common-stock, convertible-debt and straight-debt offering announcements to the issuing firms' stock price performance in periods before the announcements. Similar to previous studies on equity offerings, we find that the announcement effects of security offerings, regardless of offering types, are negatively correlated with the short-term pre-offering stock returns. We show that the informational impact of the preceding earnings and dividend(E/D) announcements account for the previous findings of the negative correlation. We further report that security issues following 'good-news' E/D announcements result in larger stock price declines than issues following 'bad-news' E/D announcements. The finding is consistent with the hypothesis that the E/D information affects the investors' assessments of the firm's cash flow expectations and of the probability of external financing.