• 지능정보연구
• /
• 제20권2호
• /
• pp.59-71
• /
• 2014

KOSPI200 선물 트레이딩을 위해 업계에서는 여러 전략으로 포트폴리오를 구성해서 운용한다. 동일한 전략 모음을 갖고 있더라도 포트폴리오를 어떻게 구성하느냐에 따라 수익은 크게 차이가 난다. 시장 상황에 맞는 전략들로 포트폴리오를 구성하는 것은 오랜 경험과 탁월한 노하우가 있어야하는 어려운 작업이다. 본 논문에서는 SVM을 활용하여 쉽고 빠르게 적절한 전략 포트폴리오를 구성하는 방법을 제시하였다. 본 논문에서 제안한 시스템의 성과는 벤치마킹의 성과와 비교하여 2배 이상의 수익을 내는 것을 확인하였다. 1990.01.03~2011.11.04 동안의 KOSPI200 데이터 중 이전 80%의 데이터로 학습을 하고 최근 20%의 데이터로 성능을 시험하였다. 각 전략별로 선택여부를 판별하는 SVM모델을 만들고 그 결과를 바탕으로 포트폴리오를 구성하였다. 벤치마킹을 위해 KOSPI200 선물을 2계약 매수한 경우의 수익, 시험 시작 직전 30일간 최고 수익을 낸 2개 전략의 수익, 실제 최고 수익을 낸 전략 2개를 보유했을 때의 수익과 비교하였다. 매매 비용을 반영하지 않을 때는 벤치마킹은 132.2~510.37pt의 수익을 냈고, 본 시스템은 1072.36~1140.91pt의 수익을 보여주었다. 그리고 거래비용을 감안하면 벤치마킹은 130.44~502.41pt의 수익을 냈고, 본 시스템은 706.22pt~768.95pt의 수익을 나타내었다. 본 논문은 기계학습을 통한 전략 포트폴리오를 구성하는 방안이 유의미하며 실전에 활용할 수 있음을 보여주었다. 이를 바탕으로 여러 전략과 다양한 시장에 적용해서 안정성을 검증하면 견고한 상용 솔루션으로 발전시킬 수 있을 것이다. 그리고 자금관리 기법을 더 반영한다면 수익을 더욱 크게 향상시킬 수 있을 것이다.

• Journal of Mechanical Science and Technology
• /
• 제15권5호
• /
• pp.639-645
• /
• 2001

Experimental investigations were conducted to study forced convection of fully developed turbulent flows in horizontal equilateral triangular ducts with different surface roughness pitch ratios (P/e) of 4, 8, and 16 on one side. The ducts bottom wall was heated uniformly and the other surfaces were thermally insulated. To understand heat transfer enhancement mechanism, heat transfer rates were measured. Smooth triangular ducts were also tested for benchmark purposes. The results were compared with previous results for similarly configured channels, at which they were roughened by regularly spaced transverse ribs in the rectangular and circular channels.

• East Asian Economic Review
• /
• 제21권2호
• /
• pp.147-165
• /
• 2017

This study quantifies the dynamic interrelationship between the KOSPI index return and search query data derived from the Naver DataLab. The empirical estimation using a bivariate GARCH model reveals that negative contemporaneous correlations between the stock return and the search frequency prevail during the sample period. Meanwhile, the search frequency has a negative association with the one-week- ahead stock return but not vice versa. In addition to identifying dynamic correlations, the paper also aims to serve as a test bed in which the existence of profitable trading strategies based on big data is explored. Specifically, the strategy interpreting the heightened investor attention as a negative signal for future returns appears to have been superior to the benchmark strategy in terms of the expected utility over wealth. This paper also demonstrates that the big data-based option trading strategy might be able to beat the market under certain conditions. These results highlight the possibility of big data as a potential source-which has been left largely untapped-for establishing profitable trading strategies as well as developing insights on stock market dynamics.

• ETRI Journal
• /
• 제33권1호
• /
• pp.39-49
• /
• 2011

A new structure learning approach for Bayesian networks based on asexual reproduction optimization (ARO) is proposed in this paper. ARO can be considered an evolutionary-based algorithm that mathematically models the budding mechanism of asexual reproduction. In ARO, a parent produces a bud through a reproduction operator; thereafter, the parent and its bud compete to survive according to a performance index obtained from the underlying objective function of the optimization problem: This leads to the fitter individual. The convergence measure of ARO is analyzed. The proposed method is applied to real-world and benchmark applications, while its effectiveness is demonstrated through computer simulations. Results of simulations show that ARO outperforms genetic algorithm (GA) because ARO results in a good structure and fast convergence rate in comparison with GA.

• Journal of Computing Science and Engineering
• /
• 제4권4호
• /
• pp.276-290
• /
• 2010

The join operator is fundamental in relational database systems. Evaluating join queries on large tables is challenging because records need to be efficiently matched based on a given key. In this work, we analyze join queries in SQL with large tables in which a foreign key may be null, invalid or valid, given a referential integrity constraint. We conduct an extensive join performance evaluation on three DBMSs. Specifically, we study join queries varying table sizes, row size and key probabilistic distribution, inserting null, invalid or valid foreign key values. We also benchmark three well-known query optimizations: view materialization, secondary index and join reordering. Our experiments show certain optimizations perform well across DBMSs, whereas other optimizations depend on the DBMS architecture.

• Structural Engineering and Mechanics
• /
• 제46권2호
• /
• pp.231-244
• /
• 2013

An efficient method is proposed here to identify multiple damage cases in structural systems using the concepts of flexibility matrix and strain energy of a structure. The flexibility matrix of the structure is accurately estimated from the first few mode shapes and natural frequencies. Then, the change of strain energy of a structural element, due to damage, evaluated by the columnar coefficients of the flexibility matrix is used to construct a damage indicator. This new indicator is named here as flexibility strain energy based index (FSEBI). In order to assess the performance of the proposed method for structural damage detection, two benchmark structures having a number of damage scenarios are considered. Numerical results demonstrate that the method can accurately locate the structural damage induced. It is also revealed that the magnitudes of the FSEBI depend on the damage severity.

• 국제초고층학회논문집
• /
• 제3권3호
• /
• pp.191-198
• /
• 2014

The tall building and super tall building has been a common building type in China, with multiple functions and complex geometry. Composite construction is broadly used in tall building structures and constitutes the mixed structure together with concrete and steel constructions. The mixture of the constructions is purposely designed for specific area based on the analysis results to achieve the best cost-effectiveness. New types of composite construction are conceived of by engineers for columns and walls. Material distribution is more flexible and innovative in the structural level and member level. However the reliability of computer model analysis should be verified carefully. Further researches in the design and build of composite construction are necessary to ensure the success of its application. Composite or Mixture Index is suggested to be used as a performance benchmark.

• 한국자동차공학회논문집
• /
• 제21권5호
• /
• pp.113-120
• /
• 2013

This paper presents a mathematical model to determine the optimal length of static messages that can achieve more efficient use of a FlexRay network. In order to determine the optimal length of static message, the proposed model evaluates the given set of messages with respect to a network utilization index, which is defined in this work. The efficient use of a FlexRay network is achieved by reallocating any static message whose length is equal or greater than the resulting value to the dynamic segment. The effectiveness of the proposed method is investigated by applying to the SAE benchmark data.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.863-875
• /
• 2017

The traditional text similarity measurement methods based on word frequency vector ignore the semantic relationships between words, which has become the obstacle to text similarity calculation, together with the high-dimensionality and sparsity of document vector. To address the problems, the improved singular value decomposition is used to reduce dimensionality and remove noises of the text representation model. The optimal number of singular values is analyzed and the semantic relevance between words can be calculated in constructed semantic space. An inverted index construction algorithm and the similarity definitions between vectors are proposed to calculate the similarity between two documents on the semantic level. The experimental results on benchmark corpus demonstrate that the proposed method promotes the evaluation metrics of F-measure.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2015년도 추계학술발표대회
• /
• pp.1248-1250
• /
• 2015

MySQL 데이터베이스에서 사용하는 Non-clustered Secondary Index는 디스크 접근 시 Random한 입출력을 유발하여 디스크 장치의 성능을 저하시키는 문제점을 가지고 있다. 이를 해결하기 위해 MySQL의 Storage Engine은 Insert Buffer를 사용하여 Random한 디스크 접근을 방지한다. Benchmark를 통해 성능 평가를 진행한 결과 Insert Buffer를 사용하는 것만으로 성능이 개선되는 것을 확인하였다. 또한, 현재의 Insert Buffer를 수정하여 더 큰 성능 향상을 이끌어낼 수 있는 부분을 발견하여 이에 대한 아이디어를 제시, 간단한 구현을 통해 추가적인 성능 향상을 보였다.