• 벤처창업연구
• /
• 제17권1호
• /
• pp.229-249
• /
• 2022

본 연구는 다양한 머신러닝 기법을 통해 코스닥(KOSDAQ) 시장 내 관리종목 지정을 예측할 수 있는 모델에 대해 연구하였다. 증권시장 내 기업이 관리종목으로 지정이 되면 시장에서는 이를 부정적인 정보로 인식하여 해당 기업과 투자자에게 손실을 가져오게 된다. 본 연구를 통해 기업의 재무적 데이터를 바탕으로 조기에 관리종목 지정을 예측하고, 투자자들의 포트폴리오 리스크 관리에 도움을 주기 위한 머신러닝 접근이 타당한지 살펴본다. 본 연구를 위해 활용한 독립변수는 수익성, 안정성, 활동성, 성장성을 나타내는 21개의 재무비율을 활용하였으며, K-IFRS가 적용된 2011년부터 2020년까지 관리종목과 비관리종목의 기업의 재무 데이터를 표본으로 추출하였다. 로지스틱 회귀분석, 의사결정나무, 서포트 벡터 머신, 랜덤 포레스트, LightGBM을 활용하여 관리종목 지정 예측 연구를 수행하였다. 연구결과는 분류 정확도가 82.73%인 LightGBM이 가장 우수한 예측 모형이었으며 분류 정확도가 가장 낮은 예측 모형은 정확도가 71.94%인 의사결정나무였다. 의사결정나무 기반 학습 모형의 변수 중요도의 상위 3개 변수를 확인한 결과 각 모형에서 공통적으로 나온 재무변수는 ROE(당기순이익), 자본금회전율(Capital stock turnover ratio)로 해당 재무변수가 관리종목 지정에 있어 상대적으로 중요한 변수임을 확인하였다. 대체적으로 앙상블을 이용한 학습 모형이 단일 학습 모형보다 예측 성능이 높은 것을 확인하였다. 기존 선행연구가 K-IFRS에 대한 고려를 하지 않았고, 다소 제한된 머신러닝에 의존하였다. 따라서 본 연구의 필요성과 함께 현실적 요구를 충족시키는 결과를 제시하였음을 알 수 있으며, 시장참여자들에게 있어 관리종목 지정에 대한 사전 예측을 확인할 수 있도록 기여했다고 볼 수 있다.

• 벤처창업연구
• /
• 제18권6호
• /
• pp.147-157
• /
• 2023

최근 벤처기업 육성을 위한 제2벤처 붐 확산 등에 힘입어 전문투자자 뿐만 아니라 일반 개인까지 스타트업 시장에 대한 관심이 증가하고 있다. 이와 같은 투자자 다변화에 따라 최근 엔젤투자자를 대상으로 다양한 연구가 진행되고 있으나 그들의 투자기업 선정 시 어떠한 요인을 고려하는지에 대해서는 주로 설문조사를 기반으로 연구가 이루어진 상황이다. 따라서 엔젤투자자가 실제로 투자한 기업내역을 토대로 그들이 어떠한 기업특성을 고려하는지에 대해 보다 엄정하게 고찰할 필요가 있다. 본 연구는 첫쨰, 엔젤투자자의 투자결정에 있어 어떠한 재무적 특성이 영향을 미치는지를 분석하였다. 둘째, 스타트업의 업력을 기준으로 창업 초기 또는 창업 중기단계 이후의 기업을 구분한 후 세부적인 분석을 수행하였다. 본 연구의 주요 분석결과를 요약하면 다음과 같다. 첫째, 엔젤투자자의 투자기업 선정에 있어 수익성이나 안정성보다는 순이익증가율이나 자산증가율과 같은 성장성 측면이 중요한 요인으로 작용하였다. 또한, 무형자산과 R&D 비중이 높을수록 투자기업을 선택할 가능성이 높은 것으로 확인된다. 둘째, 엔젤투자자의 투자기업 선정을 위한 재무적 요인에 있어 업력이 3년을 초과하여 본격적으로 창업 중기단계에 진입한 기업에서는 성장성 뿐만 아니라 활동성 측면도 투자결정에 영향을 미치는 것으로 나타났다. 종합하면, 엔젤투자자의 투자의사 결정은 기 실현된 수익성 보다는 스타트업의 성장세나 향후 성장 가능성에 중점을 두고 행해지는 것으로 판단된다. 또한, 창업 중기 이후의 기업은 성장성과 함께 실질적인 성과창출 가능성도 중요한 투자결정 요인인 것으로 추론해 볼 수 있다. 본 연구는 엔젤투자자가 실제로 투자한 내역을 기초로 다양한 스타트업의 재무적 특성을 고려하여 그들의 투자결정에 어떠한 측면이 중요하게 작용하는지를 실증적으로 규명하였다는 점에서 연구의 의의가 있다.

• 경영과정보연구
• /
• 제22권
• /
• pp.137-165
• /
• 2007

It seems high time to increase productivity by adopting e-business to overcome challenges posed by both external factors including the appreciation of Korean won, oil hikes and fierce global competition and domestic issues represented by disparities between large corporations and small and medium enterprises (SMEs), Seoul metropolitan and local cities, and export and domestic demand all of which weaken future growth engines in the Korean economy. The demands of the globalization era are for innovative changes in businessprocess and industrial structure aiming for creating new values. To this end, e-business is expected to play a core role in the sophistication of the Korean economy through new values and innovation. In order to examine business performance in e-business-adopting industries, this study analyzed the home shopping industry by closely looking into the financial ratios including the ratio of net profit to sales, the ratio of operation income to sales, the ratio of gross cost to sales cost, the ratio of gross cost to selling, general and administrative (SG&A) expense, and return of investment (ROI). This study, for best outcome, referred to corporate financial statements as a main resource to calculate financial ratios by utilizing Data Analysis, Retrieval and Transfer System (DART) of the Financial Supervisory Service, one of the Korea's financial supervisory authorities. First of all, the result of the trend analysis on the ratio of net profit to sales is as following. CJ Home Shopping has registered a remarkable increase in its ratio of net profit rate to sales since 2002 while its competitors find it hard to catch up with CJ's stunning performances. This is partly due to the efficient management compared to CJ's value of capital. Such significance, if the current trend continues, will make the front-runner assume the largest market share. On the other hand, GS Home Shopping, despite its best organized system and largest value of capital among others, lacks efficiency in management. Second of all, the result of the trend analysis on the ratio of operation income to sales is as following. Both CJ Home Shopping and GS Home Shopping have, until 2004, recorded similar growth trend. However, while CJ Home Shopping's operating income continued to increase in 2005, GS Home Shopping observed its operating income declining which resulted in the increasing income gap with CJ Home Shopping. While CJ Home Shopping with the largest market share in home shopping industryis engaged in aggressive marketing, GS Home Shopping due to its stability-driven management strategies falls behind CJ again in the ratio of operation income to sales in spite of its favorable management environment including its large capital. Companies in the Group B were established in the same year of 2001. NS Home Shopping was the first in the Group B to shift its loss to profit. Woori Home Shopping has continued to post operating loss for three consecutive years and finally was sold to Lotte Group in 2007, but since then, has registered a continuing increase in net income on sales. Third of all, the result of the trend analysis on the ratio of gross cost to sales cost is as following. Since home shopping falls into sales business, its cost of sales is much lower than that of other types of business such as manufacturing industry. Since 2002 in gross costs including cost of sales, SG&A expense, and non-operating expense, cost of sales turned out to have remarkably decreased. Group B has also posted a notable decline in the same sector since 2002. Fourth of all, the result of the trend analysis on the ratio of gross cost to SG&A expense is as following. Due to its unique characteristics, the home shopping industry usually posts ahigh ratio of SG&A expense. However, more than 80% of SG&A expense means the result of lax management and at the same time, a sharp lower net income on sales than other industries. Last but not least, the result of the trend analysis on ROI is as following. As for CJ Home Shopping, the curve of ROI looks similar to that of its investment on fixed assets. As it turned out, the company's ratio of fixed assets to operating income skyrocketed in 2004 and 2005. As far as GS Home Shopping is concerned, its fixed assets are not as much as that of CJ Home Shopping. Consequently, competition in the home shopping industry, at the moment, is among CJ, GS, Hyundai, NS and Woori Home Shoppings, and all of them need to more thoroughly manage their costs. In order for the late-comers of Group B and other home shopping companies to advance further, the current lax management should be reformed particularly on their SG&A expense sector. Provided that the total sales volume in the Internet shopping sector is projected to grow over 20 trillion won by the year 2010, it is concluded that all the participants in the home shopping industry should put strategies on efficient management on costs and expenses as their top priority rather than increase revenues, if they hope to grow even further after 2007.

• 한국임상보건과학회지
• /
• 제2권1호
• /
• pp.1-16
• /
• 2014

Purpose. For a more efficient hospital management, this study aims to provide basic data so that the hospital management and staff in charge of hospital administration may systematically classify and collect hospital information, by analyzing the ordinary characters of an upper-level general hospital system and its common-type balance sheet, common-type profit and loss statement and financial ratio. Methods. By using information about an upper-level general hospital in C Province, provided by Alio(www.alio.go.kr), a public organization information provision site, Health Insurance Review & Assessment Service(www.hira.or.kr) and Ministry of Health and Welfare(www.mw.go.kr), this study analyzed 3 year's data from 2010 to 2012 and provided basic data by analyzing the ordinary characters of an upper-level general hospital system, and its common-type balance sheet, common-type profit and loss statement and financial ratio. Results. After analyzing the ordinary characters, common-type balance sheet, common-type proft and loss statement and financial ration of this general hospital, based on the 2010 to 2012 data, this study came to the following conclusions. Firstly, out of all the 1,069 hospital staff, there were 272 doctors working for 24 medical departments, out of whom the majority was 33 physicians. Most of the nurses were third-class ones, and about 2,000 outpatients and 600 inpatients on average were treated per day. Secondly, as a result of analyzing the common-type balance sheet, this study discovered that intangible assets out of fixed assets accounted for 41%, the majority, out of which usable and profitable donation asset buildings were of great importance, and the liquid assets increased more in 2012 than 2011. In the financial structure, the ratio of liquid liabilities was over 50% out of all the liabilities in 2012, and the ratio of purchase payables was high as well. The ratio of fixed liabilities reached up to 40%, out of which the retirement benefit appropriation fund was quite high. The capital was over 80%, but the surplus was in a deficit state. Compared to the capital, the ratio of total liabilities was about 90%, which indicates the financial structure of this general hospital was vulnerable. Thirdly, as a result of analyzing the common-type profit and loss statement, this study found out that the medical profits from inpatients were higher than profits from outpatients. The material cost was related to the medical quality of this general hospital, and it was as high as 30% out of the total costs and was about 45% of the labor cost. This general hospital showed 10% in the ratio of non-medical profits, and it seemed because of government subsidies. The ratios of medical profits and current net income were gradually changing for the better in 2012, compared to 2011. Lastly, as a result of analyzing the financial ratio, it was found that the liquidity ratio kept decreasing, from 110.7% in 2010 and 102.0% in 2011 to 77.2% in 2012. Besides, it was analyzed that the liquidity ratio and the net working capital ratio greatly decreased, while the quick ratio and the liquid ratio kept decreasing. Conclusions. 1. It is necessary to take the risk management into more consideration, and particularly, it is needed to differentiate and manage the levels of risk in detail. 2. By considering the fact that investments into hospital infrastructures were mostly based on liabilities, it is needed to deal with the scale of losses when evaluating risks. 3. By reflecting the character that investments into hospital infrastructures were based on liabilities, it is necessary to consider the ratio of ordinary profits as well as the ratio of operating profits to sales, and it is also important to consider sales productivity factors, such as the sales amount per a sickbed, by comparing them with other hospitals. As for limitations of this study, there may be some problems in terms of data interpretation because of the lack of information about the number of inpatients and the number of outpatients per year, which are needed for the break-even point analysis. Besides, to suggest a direction for the improvement of hospital management through analyses, non-financial factors should be reflected, such as the trend of economy, medical policies, and politic backgrounds. However, this study only focused on the common-type balance sheet, common-type profit and loss statement and financial ratio, so this study is actually limited to generalizing all the factors by analyzing public data only.

• Management Science and Financial Engineering
• /
• 제20권1호
• /
• pp.21-26
• /
• 2014

A lot of researches have been conducted to estimate the volatility smile effect shown in the option market. This paper proposes a method to approximate an implied volatility function, given noisy real market option data. To construct an implied volatility function, we use Gaussian Processes (GPs). Their output values are implied volatilities while moneyness values (the ratios of strike price to underlying asset price) and time to maturities are as their input values. To show the performances of our proposed method, we conduct experimental simulations with Korean Equity-Linked Warrant (ELW) market data as well as toy data.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2011년도 춘계학술논문집 2부
• /
• pp.1029-1032
• /
• 2011

가장 전형적이고 대표적인 재무분석 기법인 재무비율 분석 방법을 이용하여 내항공업계에서 시장점유율 2위인 사례기업을 경쟁 기업인 D 항공과의 비교 검토를 통하여 재무적 강약점을 분석하였다. 그 결과 수익성은 최근 들어 크게 개선되어 경쟁사를 앞서고 있는데 이는 효율적인 자산의 관리에서 기인한 바 큰 것으로 분석되었다. 유동성 및 안정성은 경쟁사에 비해 양호한 것으로 보이나 방어기간 면에서는 다소 취약한 것으로 분석되었다. 종합적으로 보면 경쟁사에 비하여 전반적으로 뒤떨어져 있던 경쟁력이 근래 들어 개선되고 있음으로 각종 재무 지표는 보여주고 있다.

• 유통과학연구
• /
• 제11권3호
• /
• pp.5-11
• /
• 2013

Purpose - Going concern is one of fundamental concepts in accounting and auditing and sometimes the assessment of a company's going concern status that is a tough process. Various going concern prediction models' based on statistical and data mining methods help auditors and stakeholders suggested in the previous literature. Research design - This paper employs a data mining approach to prediction of going concern status of Iranian firms listed in Tehran Stock Exchange using Particle Swarm Optimization. To reach this goal, at the first step, we used the stepwise discriminant analysis it is selected the final variables from among of 42 variables and in the second stage; we applied a grid-search technique using 10-fold cross-validation to find out the optimal model. Results - The empirical tests show that the particle swarm optimization (PSO) model reached 99.92% and 99.28% accuracy rates for training and holdout data. Conclusions - The authors conclude that PSO model is applicable for prediction going concern of Iranian listed companies.

• 한국지하수토양환경학회:학술대회논문집
• /
• 한국지하수토양환경학회 2004년도 임시총회 및 추계학술발표회
• /
• pp.115-118
• /
• 2004

The purpose of this research is to investigate the noble gas isotope and the hydrochemical characteristics of hot springs in the Chungcheong area in Korea. This study was carried. out by the financial support of Korea-Japan joint research program of KOSEF, Noble gases are very useful tracers to investigate volatile elements circulation, because of their unique isotopic compositions in various reservoirs of the Earth. Isotopic ratios of noble gases has been carried out for If hot-spring samples from Daejon and its near areas in Korea last January 2004. Helium isotope ratio gave the evidence that helium gas of different origins(air-crust mixing origin, crust-origin and mantle-origin) is supplied into hot-spring waters in Korea. We found the distinct relationship between temperature of hot springs and helium gas origin.

• 유통과학연구
• /
• 제12권3호
• /
• pp.33-41
• /
• 2014

Purpose - The purpose of this study was to predict the selection of independent auditors in the companies listed on the Tehran Stock Exchange (TSE) using a combination of PSO algorithm and CART. This study involves applied research. Design, approach and methodology - The population consisted of all the companies listed on TSE during the period 2005-2010, and the sample included 576 data specimens from 95 companies during six consecutive years. The independent variables in the study were the financial ratios of the sample companies, which were analyzed using two data mining techniques, namely, PSO algorithm and CART. Results - The results of this study showed that among the analyzed variables, total assets, current assets, audit fee, working capital, current ratio, debt ratio, solvency ratio, turnover, and capital were predictors of independent auditor selection. Conclusion - The current study is practically the first to focus on this topic in the specific context of Iran. In this regard, the study may be valuable for application in developing countries.

• 한국정보시스템학회지:정보시스템연구
• /
• 제4권
• /
• pp.27-39
• /
• 1995

This study tests the fuzzy linear regression model to see if there is a performance difference between it and the classical linear regression model. These results show that FLR was better as f forecasting technique when compared with CLR. Another important find in the test of the two different regression methods is that they generate two different predicted P/E ratios from expected value test, variance test and error test of two different regressions, though we can not see a significant difference between two regression models doing test in error measurements (GMRAE, MAPE, MSE, MAD). So, in this financial setting we can conclude that FLR is not superior to CLR, comparing and testing between the t재 different regression models. However, FLR is better than CLR in the error measurements.