• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권9호
• /
• pp.367-374
• /
• 2021

주가 예측은 경제, 통계, 컴퓨터 공학 등 여러 분야에서 연구되는 주제이며, 특히 최근에는 기본적 지표나 기술적 지표 등 다양한 지표로부터 인공지능 모델을 학습하여 주가의 변동을 예측하는 연구들이 활발해 지고 있다. 본 연구에서는 S&P500 등의 해외지수, 과거 KOSPI 지수, 그리고 KOSPI 투자자별 매매 동향으로부터 KOSPI의 등락을 예측하는 딥러닝 모델을 제안한다. 제안 모델은 주가 등락 예측을 위하여 비지도 학습 방법인 적층 오토인코더를 이용하여 잠재변수를 추출하고, 추출된 잠재변수로부터 시계열 데이터 학습에 적합한 LSTM 모델로 학습하여 당일 시가 대비 종가의 등락을 예측하며, 예측된 값을 기반으로 매수 또는 매도를 결정한다. 본 연구에서 제안하는 모델과 비교 모델들의 수익률 및 예측 정확도를 비교한 결과 제안 모델이 비교 모델들 보다 우수한 성능을 보였다.

• 경영과학
• /
• 제30권1호
• /
• pp.73-89
• /
• 2013

This paper develops an investment algorithm based on Markowitz's Portfolio Selection Theory, using historical stock return data, and empirically evaluates the performance of the proposed algorithm in the U.S. and the Hong Kong stock markets. The proposed investment algorithm is empirically tested with the 30 constituents of Dow Jones Industrial Average in the U.S. stock market, and the 30 constituents of Hang Seng Index in the Hong Kong stock market. During the 6-year investment period, starting on the first trading day of 2006 and ending on the last trading day of 2011, growth rates of 12.63% and 23.25% were observed for Dow Jones Industrial Average and Hang Seng Index, respectively, while the proposed investment algorithm achieved substantially higher cumulative returns of 35.7% in the U.S. stock market, and 150.62% in the Hong Kong stock market. When compared in terms of Sharpe ratio, Dow Jones Industrial Average and Hang Seng Index achieved 0.075 and 0.155 each, while the proposed investment algorithm showed superior performance, achieving 0.363 and 1.074 in the U.S. and Hong Kong stock markets, respectively. Further, performance in the U.S. stock market is shown to be less sensitive to an investor's risk preference, while aggressive performance goals are shown to achieve relatively higher performance in the Hong Kong stock market. In conclusion, this paper empirically demonstrates that an investment based on a mathematical model using objective historical stock return data for constructing optimal portfolios achieves outstanding performance, in terms of both cumulative returns and Sharpe ratios.

• 전기전자학회논문지
• /
• 제23권3호
• /
• pp.852-857
• /
• 2019

분산자원 집합 거래시장에 참여를 원하는 소비자나 사업자를 위한 가상발전소의 전력거래 플랫폼에서 사업참여자의 수요 자원을 관리하고, 이에 적절한 전략을 제공하기 위해 익일 개별 참여자의 수요와 전체 계통의 전력수요를 예측하는 것이 대단히 중요하다. 이러한 전력거래 플랫폼에서 활용하는 것을 목표로 본 논문은 우선 익일의 24시간 전력계통 전력수요예측 모델을 개발하였다. 본 논문에서는 전력수요예측 데이터의 시계열 특성을 고려하여 딥러닝 기법 중 LSTM 알고리즘을 사용하였고, 전력수요량 등의 입출력 값에 원-핫 인코딩 기법을 적용하는 새로운 시도를 하였다. 성능평가에서 일반 DNN과 본 논문에서 구현된 LSTM 예측모델은 각각 평균 제곱근 오차 4.50, 1.89를 나타내어 LSTM 모델이 예측정확도가 높게 나타났다.

• 유통과학연구
• /
• 제15권5호
• /
• pp.29-38
• /
• 2017

Purpose - Prior theories predict a negative correlation between stock liquidity and dividend payout propensity. We test this hypothesis by examining the sample Korean retail firms. Research design, data, and methodology - We construct four different types of stock liquidity measures and investigate how these stock liquidity variables affect dividend payout propensity by employing the logit regression model. The retail firms listed in the KOSPI and KOSDAQ markets are analyzed from 1990 to 2015. Results - Our estimation results support the liquidity hypothesis if we adopt the stock turnover rate as the stock liquidity measure, particularly for the retail firms listed in the KOSPI markets and for non-conglomerate firms. Yet, our estimation results adopting the illiquidity measure of Amihud (2002), the proportion of non-trading day, and the volume of trading do not support the liquidity hypothesis. Conclusions - Our findings provide mixed results for the validity of stock liquidity hypothesis, which enriches the existing literature. In terms of turnover rate, the stock liquidity hypothesis holds robustly. Yet, we are not able to find any empirical evidence supporting the hypothesis if we use the other three measures of stock liquidity.

• 산업융합연구
• /
• 제7권1호
• /
• pp.63-82
• /
• 2009

Many The purpose of this paper is to revisit the existence of monthly effect in the Korea Stock Market. We conducted additory test about KOSPI200 from January 1990 to December 2002 and about KOSDAQ from January 2002 to December 2006. The other main focus is examine Size Effect in Korean Stock Market. We also indicate Information hypothesis throught our findig. Data used in this paper are monthly returns of KOSPI and KOSDAQ from 1980 to 2006. As a result, Evidence is provided that monthly abnormal returns in January have large means relative to the remaining eleven months. The relation between abnormal returns and size is always negative and more pronounced in January than in any other month-even in years. More than fifty percent of the January premium is attributable to large abnormal returns during the first week of trading in the year particularly on the first trading day. This finding is highly significant in the mall sized capital stock of KOSPI market. We found January effect and Size Effect in the KOSPI market, but we didn't find January effect and Size Effect in the KOSDAQ market and KOSPI200.

• 유통과학연구
• /
• 제10권7호
• /
• pp.5-11
• /
• 2012

The core objective of this research article is to investigate different challenges and opportunities in management as well as start-ups of small businesses in India. The prudence behind this research is to examine various problems in front of the small businesses and to offer vital support and cooperation to overcome those with the support of concerned institutions through consultancy and training programs. The researchers have an intention to make available the research results to the governmental agencies, concerned small business institutions and also to the educational institutions which are continually design plans, programs, policies and strategies to upgrade the managerial and technical dexterities of the small business Indian operators. After thorough revision of relevant literature on small businesses and its management, the researchers used a well structured questionnaire and in-depth personal interviews with 586small business operators selected from manufacturing, trading (retailing and wholesaling), finance, servicing/repair businesses which are located in the coastal districts of Andhra Pradesh in India. The researchers have used convenience sampling and collected data was analyzed with the support of Microsoft Excel and frequency distribution. Noticeably, majority of the small businessmen in India are facing myriad number of challenges both in management and at the time of establishment of their business operations. In particular, 72.47 percent of small businesses operators' have substantiated their strong opinion towards the challenges they are facing particularly finance, marketing and other problems while managing their businesses. The researchers also attempted to get the opinions on problems of the various categories of small businesses while starting their operations. A staggering 68percent of respondents identified the problems related to preparation of business plan, location selection, marketing and other problems like lack of proper credit facilities, skilled manpower, and other infra related problems while setting up of their businesses. On an average, 64.62 and 63.51 percent of small businesses are facing various kinds of problems both at the time of day-to-day management as well as start-up of their businesses respectively. The present research confined with the opinions of only four categories of small business operators particularly from the manufacturing, finance, trading (retailing and wholesaling), and servicing/repair which are continuing their business operations from the nine coastal districts of Andhra Pradesh in India. The present study emphatically provides concrete information required to the business community for identifying an assortment of challenges faced by different small business operators in managing and at the time of their inception. This research paper is first of its kind from this part of the world by offering extensive and credible information required for prospective entrepreneurs in facing the dynamic challenges in managing their business. Furthermore, this research presents invaluable inputs to the stakeholders like all types of governments, policy makers, practitioners, researchers, and educators' about the various impediments faced by the small business community in India.

• 재무관리연구
• /
• 제27권2호
• /
• pp.145-167
• /
• 2010

본 연구는 주식시장의 종가 대비 일별 수익률을, 외국 경제 정보가 반영된 비거래 시간대의 밤 수익률(전일 종가 대비 당일 시가)과 국내 경제 정보가 반영된 거래 시간대의 낮 수익률(당일 시가 대비 종가)로 구분하여, 주가 수익률과 투자 주체의 역동적 상호 관계를 분석하였다. 전체적인 결과는 다음과 같다. 외국인은 당일 낮 수익률보다는 밤 수익률에 더 크게 영향을 받는데 비하여, 개인 투자자는 당일 밤 수익률보다는 낮 수익률에 영향을 더 받는다. 또한, 외국인의 순매수를 설명하는 요인으로 밤 수익률의 분산 설명력이 낮 수익률보다 더 높으며, 개인 투자자의 순매수는 외국인의 순매수를 설명하지 못했다. 반대로 개인 투자자의 순매수에 대해서는 낮 수익률과 외국인 순매수의 분산 설명력이 상대적으로 높게 나타났다. 이와 같은 결과로 볼 때, 외국인은 국내의 경제 상황 변화보다는 외국의 경제 상황에 민감하게 반응하는 투자 전략을 취한다고 할 수 있다. 반면에 개인 투자자는 외국의 경제 상황보다는 국내 경제 상황에 치중하는 투자 전략을 취하고 있다. 따라서 외국인과 개인 투자자의 거래를 유발하는 경제적 요인이 서로 다른 측면이 있다고 하겠다. 이는 세계적 금융 위기가 구체화 되었던 2008년 8월 이후 우리 주식시장의 현상과도 일치한다.

• 대한전기학회논문지:전력기술부문A
• /
• 제55권2호
• /
• pp.85-93
• /
• 2006

Since the SMP(System Marginal Price) is a vital factor to the market participants who intend to maximize the their profit and to the ISO(Independent System Operator) who wish to operate the electricity market in a stable sense, the short-term marginal price forecasting should be performed correctly. In an electricity market the short-term market price affects considerably the short-term trading between the market entities. Therefore, the exact forecasting of SMP can influence on the profit of market participants. This paper presents a new methodology for a day-ahead SMP forecasting using ARIMA(Autoregressive Integrated Moving Average) model based on the time-series method. And also the correction algorithm is proposed to minimize the forecasting error in order to improve the efficiency and accuracy of the SMP forecasting. To show the efficiency and effectiveness of the proposed method, the case studies are performed using historical data of SMP in 2004 published by KPX(Korea Power Exchange).

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 하계학술대회 논문집 A
• /
• pp.550-552
• /
• 2001

The vertically integrated power industry was divided into six generation companies and one market operator, where electricity trading was launched at power exchange. In this environment, the profits of each generation companies are guaranteed according to utilization of their own generation equipments. Especially, the electricity demand shows seasonal and weekly regular pattern, which the some capacity should be provided into ancillary service based on the past demand forecasting error and operating results of electricity market. Namely, if generation cost function is applied to SMP and BLMP as announced the previous day, the available generation capacity of the following day could be optimally distributed, and therefore contract capacity of ancillary service applied to CBP(Cost Based Pool) and TWBP(Two-Way Bidding Pool) is determined. Consequently, it is Possible to use the retained equipments optimally. This paper represents on efficient bidding strategies for generation equipments through the calculation of the contract and the application of each generator cost function based on the past demand forecasting error and market operating data.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권11호
• /
• pp.95-100
• /
• 2020

Nifty Bank Index has started trading in futures and options (F&O) segment from 13^th June 2005 in National Stock Exchange. The purpose of the study is to enhance the literature by examining expiration effect on the price volatility and price reversal of Underlying Index in India. Historical data used for the current study primarily comprise of daily close prices of Nifty Bank which is the only equity sectoral index in India which is traded in derivatives market and its Future contract value is derived from the underlying CNX Bank Index during the period 1^st January 2010 till 31^st March 2020. To check stationarity of the data, Augmented Dicky Fuller test was used. The study employed ARMA- EGARCH model for analysing the data. The empirical results revealed that there is no effect on the mean returns of underlying Index and EGARCH (1,1) model furthermore shows there is existence of leverage effect in the Bank Index i.e., negative shocks causes more fluctuations in the Index than positive news of similar magnitude. The outcome of the study specifies that there is no effect on volatility on the underlying sectoral index due to expiration days and also observed no price reversal effect once the expiration days are over.