• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.1-7
• /
• 2022

In this paper, a study was conducted to predict natural disasters in Afghanistan based on machine learning. Natural disasters need to be prepared not only in Korea but also in other vulnerable countries. Every year in Afghanistan, natural disasters(snow, earthquake, drought, flood) cause property and casualties. We decided to conduct research on this phenomenon because we thought that the damage would be small if we were to prepare for it. The Azure Machine Learning Studio used in the study has the advantage of being more visible and easier to use than other Machine Learning tools. Decision Forest is a model for classifying into decision tree types. Decision forest enables intuitive analysis as a model that is easy to analyze results and presents key variables and separation criteria. Also, since it is a nonparametric model, it is free to assume (normality, independence, equal dispersion) required by the statistical model. Finally, linear/non-linear relationships can be searched considering interactions between variables. Therefore, the study used decision forest. The study found that overall accuracy was 89 percent and average accuracy was 97 percent. Although the results of the experiment showed a little high accuracy, items with low natural disaster frequency were less accurate due to lack of learning. By learning and complementing more data, overall accuracy can be improved, and damage can be reduced by predicting natural disasters.

• The Journal of Asian Finance, Economics and Business
• /
• 제9권9호
• /
• pp.351-360
• /
• 2022

This study aims to determine the factors that can influence investors in selecting stocks in the Indonesian capital market to establish an optimal portfolio, and find phenomena that occurred during the COVID-19 pandemic so that buying interest / the number of investors increased in the Indonesian capital market. This study collection technique uses primary data obtained from the survey questionnaire and secondary data which is market data, stock price movement data sourced from the Indonesia Stock Exchange, Indonesian Central Securities Depository, and Bank Indonesia, as well as empirical literature on behavior finance, investment decision, and interest in buying stock. The method used in this research is the survey questionnaire analysis with the SEM (statistical approach). The results of the analysis using SEM show that investor behavior influences the stock-buying interest, investor behavior, and the stock-buying interest influences investor decision-making. However, risk management does not influence investor-decision making. This occurs when the investigator's psychological capacity produces more decision information by decreasing all potential biases, allowing the best stock selection model to be selected. When the investigator's psychological capacity creates more decision information by reducing biases, the optimum stock selection model can be chosen.

• 한국콘텐츠학회논문지
• /
• 제22권2호
• /
• pp.545-558
• /
• 2022

본 연구의 목적은 전통적인 통계과 기계학습(Machine Learning)을 통해 중국 문화산업 기업의 재무적 곤경을 정확하게 예측하는 분석 모형을 탐색하는 데 있다. 예측모형을 구축하기 위하여 중국 128개 문화산업상장 기업의 데이터를 수집하였다. 25개 설명변수로 이뤄진 데이터베이스를 토대로 판별분석과 로지스틱 회귀(Logistic) 등 전통적인 통계 방법과 서포트 벡터 기계(SVM), 결정 트리(Decision Tree)와 랜덤 포레스트(Random Forest) 등 기계학습을 이용한 예측모형을 구축하고 각 모형의 성능 평가를 위해 Python 소프트웨어를 사용한다. 분석 결과, 예측 성능이 가장 좋은 모형은 랜덤 포레스트(Random Forest) 모형으로 95%의 정확도를 보였다. 그 다음은 서포트 벡터 기계(SVM) 모형으로 93%의 정확도를 보였다. 그 다음은 결정 트리(Decision Tree) 모형으로 92%의 정확도를 보였다. 그 다음은 판정분석 모형으로 89%의 정확도를 보였다. 예측 효과가 가장 낮은 모형은 로지스틱 회귀(Logistic) 모형으로 88%의 정확도를 보였다. 이는 중국 문화산업 기업의 재무적 곤경을 예측하면서 기계학습 모형이 전통적인 통계 모형보다 더 좋은 예측 효과를 얻을 수 있음을 설명한다.

• Communications for Statistical Applications and Methods
• /
• 제14권1호
• /
• pp.11-21
• /
• 2007

In this paper, we consider a decision-theoretic oriented, objective Bayesian inference for the difference between two normal means with unknown com-mon variance. We derive the Bayesian reference criterion as well as the intrinsic estimator and the credible region which correspond to the intrinsic discrepancy loss and the reference prior. We illustrate our results using real data analysis as well as simulation study.

• Communications for Statistical Applications and Methods
• /
• 제8권2호
• /
• pp.531-541
• /
• 2001

In this study, we compare the capabilities of the data mining tools of the most updated version objectively and provide the useful information in which enterprises and universities chose them. In particular, we compare the SAS/Enterprise Miner 3.0, SPSS/Clementine 5.2 and IBM/Intelligent Miner 6.1 which are well known and easily gotten.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2002년도 추계 학술발표회 논문집
• /
• pp.35-42
• /
• 2002

본 연구에서는 2000년 어업총조사에서 얻은 어가를 모집단으로 하여 어가경세조사를 위한 표본설계룰 하였다. 진체 어가를 전업 및 1종 겸업어가를 포함하는 부차모집단1과 2종 겸업어가로 구성된 부차모집단2로 구분하였다. 새로운 표본설계에서는 최적 집락크기를 구하고, 층화를 위해서 SAS Enterprise Miner에서 제공하고 있는 의사결정나무모형(Decision Tree Model)을 이용하였다. 층별 표본배정은 네이만 배정법을 사용하였고 두 가지 추정법을 제시하였다.

• Journal of the Korean Statistical Society
• /
• 제16권2호
• /
• pp.102-112
• /
• 1987

This paper treats the problem of estimating an arbitrary parametric function in the case when the parameter and sample spaces are countable and the decision space is arbitrary. Using the notions of a stepwise Bayesian procedure and finite admissibility, a theorem is proved. It shows that under some assumptions, every finitely admissible estimator is unique stepwise Bayes with respect to a finite or countable sequence of mutually orthogonal priors with finite supports. Under an additional assumption, it is shown that the converse is true as well. The first can be also extended to the case when the parameter and sample space are arbitrary, i.e., not necessarily countable, and the underlying probability distributions are discrete.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 추계 학술발표회 논문집
• /
• pp.275-279
• /
• 2003

We obtain the asymptotic distributions of tests statistics for various types of seasonal cointegration based on GRR estimators of Ahn and Cho (2003). These tests are useful in testing for restrictions about cointegrating vectors after Chi-square tests for CCI and common PCIV in Ahn and Cho (2003) or tests for the known CCI and the known PCIVs have been performed.

• Communications for Statistical Applications and Methods
• /
• 제8권3호
• /
• pp.885-894
• /
• 2001

Decision tree methods is the one of data mining techniques. Classification trees are used to predict a class label. When a tree grows, the conventional splitting criteria use the weighted average of the left and the right child nodes for measuring the node impurity. In this paper, new splitting criteria for classification trees are proposed which improve the interpretablity of trees comparing to the conventional methods. The criteria search only for interesting subsets of the data, as opposed to modeling all of the data equally well. As a result, the tree is very unbalanced but extremely interpretable.

• Communications for Statistical Applications and Methods
• /
• 제1권1호
• /
• pp.87-93
• /
• 1994

Consider the problem of estimating the parameter of the model in which an observable random variable is represented by a unknown scalar parameter plus another random variable and the parameter, sample, and decision spaces consist of all integers. We first characterize the class of all admissible estimators and then characterize the class of all finitely admissible estimators. Finally, we show that two classes are identical.