• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.195-204
• /
• 2022

The tourism industry is facing a crisis due to the recent COVID-19 pandemic, and it is vital to improving profitability to overcome it. In situations such as COVID-19, it would be more efficient to sell additional products other than guest rooms to customers who have visited to increase the unit price rather than adopting an aggressive sales strategy to increase room occupancy to increase profits. Previous tourism studies have used machine learning techniques for demand forecasting, but there have been few studies on cross-selling forecasting. Also, in a broader sense, a resort is the same accommodation industry as a hotel. However, there is no study specialized in the resort industry, which is operated based on a membership system and has facilities suitable for lodging and cooking. Therefore, in this study, we propose a cross-selling prediction model using various machine learning techniques with an actual resort company's accommodation data. In addition, by applying the explainable artificial intelligence XAI(eXplainable AI) technique, we intend to interpret what factors affect cross-selling and confirm how they affect cross-selling through empirical analysis.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of Korean Society of Transportation
• /
• v.19 no.3
• /
• pp.19-32
• /
• 2001

A parking facility choice model. which can be applied to analyze of the driver's parking behavioral changes in response to the local government's parking policy changes and to predict parking demand by the facility types, is developed. Under the context of the stated preference discrete choice model, socioeconomic variables and parking alternative characteristic variables are introduced as explanatory variables. A parking facility choice model for the shopping trip purpose is derived using multinomial logit model and nested logit model and the stated preference data collected in Taegu metropolitan area. The result shows that the sign of all the estimated parameters are logically consistent and the model's goodness of fit is reasonably good. As a result of the elasticity analysis of the model, the elasticity of parking cost is highest, and the elasticity of walking distance between parking place and the destination is higher than parking place searching and ingress time. This means that the parking places are supplied around the destination in the form of small-size parking place. The findings in this study is expected to provide a fundamental data for various short-term parking policy analyses and for parking facility's demand estimations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1082-1086
• /
• 2008

소양강댐 유역에서 몇 년간 계속되는 고탁수 문제가 좀처럼 개선되고 있지 않는 실정이다. 탁수발생의 원인은 여러 가지가 있지만 농경지를 중심으로 유입되는 토양유실이 가장 직접적인 원인으로 지적되고 있다. 특히, 고랭지 농경지에서 소득 작물에 대한 연작피해 경감, 작물의 생산성 향상과 농민들의 소득 증대와 연관되어 무분별하게 농경지에 행해진 객토와 농약 및 비료는 수질 악화의 매우 큰 영향을 미치고 있다. 이러한 문제로 인하여, 토양유실량 추정을 위한 여러 모형들이 개발되었다. 이 중, SWAT 모형은 미국 농무성의 농업연구소에서 개발된 유역단위 모형으로 대규모의 복잡한 유역에서 장기간에 걸친 다양한 종류의 토양과 토지이용 및 토지관리 상태에 따른 수문과 유사 및 농업화학물질의 거동에 대하여 예측하기 위해 개발된 모형이다. 이 SWAT모형은 유역내 수문 및 유사 모의시, DEM을 기반으로 유역 평균경사도를 이용하여 경사도-경사장 관계식 산정 경사장을 유역내 모든 수문학적 반응단위 (HRU: Hydrologic Response Unit)의 동일하게 적용한다. 이는 SWAT 모의 유사량과 실측 자료에 있어서 큰 차이를 초래할 수 있다. 따라서 본 연구에서는 해안면 지역의 모든 농경지에 대해 강원발전연구원에서 전수 조사한 실측 경사장 및 경사도 자료를 반영할 수 있도록 소유역내 모든 HRU에 면적 가중 경사도/경사장을 할당해 주는 프로그램을 개발하여 준분포 모형인 SWAT의 단점을 극복하였다. 그 결과 유출량의 경우 면적 가중 실측경사장 및 경사도를 적용 유무에 따라 월 평균유량 3,951,537 m3/month, 3,953,947 m3/month로 2,410 m3/month의 큰 차이를 보이지 않았지만, 유사량의 경우 면적 가중 실측경사장 및 경사도 적용 하였을 경우 10,826 ton/month 이고, 기존 SWAT 예측 유사량은 월평균 3,642 ton/month으로 7,184 ton/month (66.4 % 차이) 큰 차이를 보였다. 이러한 결과는 SWAT 모형 적용시 경사장 및 경사도 산정에 따라, 유사량이 과소 또는 과대 평가 될 수 있음을 보여준다.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1749-1758
• /
• 1997

This paper suggests the development of dynamic forecasting model for short-term power demand based on Radial Basis Function Network and Pal's GLVQ algorithm. Radial Basis Function methods are often compared with the backpropagation training, feed-forward network, which is the most widely used neural network paradigm. The Radial Basis Function Network is a single hidden layer feed-forward neural network. Each node of the hidden layer has a parameter vector called center. This center is determined by clustering algorithm. Theatments of classical approached to clustering methods include theories by Hartigan(K-means algorithm), Kohonen(Self Organized Feature Maps %3A SOFM and Learning Vector Quantization %3A LVQ model), Carpenter and Grossberg(ART-2 model). In this model, the first approach organizes the load pattern into two clusters by Pal's GLVQ clustering algorithm. The reason of using GLVQ algorithm in this model is that GLVQ algorithm can classify the patterns better than other algorithms. And the second approach forecasts hourly load patterns by radial basis function network which has been constructed two hidden nodes. These nodes are determined from the cluster centers of the GLVQ in first step. This model was applied to forecast the hourly loads on Mar. $4^{th},\;Jun.\;4^{th},\;Jul.\;4^{th},\;Sep.\;4^{th},\;Nov.\;4^{th},$ 1995, after having trained the data for the days from Mar. $1^{th}\;to\;3^{th},\;from\;Jun.\;1^{th}\;to\;3^{th},\;from\;Jul.\;1^{th}\;to\;3^{th},\;from\;Sep.\;1^{th}\;to\;3^{th},\;and\;from\;Nov.\;1^{th}\;to\;3^{th},$ 1995, respectively. In the experiments, the average absolute errors of one-hour ahead forecasts on utility actual data are shown to be 1.3795%.

• 한국방재학회:학술대회논문집
• /
• 2011.02a
• /
• pp.209-209
• /
• 2011

산지하천의 비율이 높은 국내 하천은 주로 만곡도가 높은 사행하천으로 이루어져 있으며, 만곡부가 교호적으로 나타나는 사행하천의 흐름구조는 매우 복잡하다. 산지하천의 특성상 홍수시에는 유속이 매우 빠르게 나타나며 하천의 수위가 상승하게 될 때 만곡부에서의 흐름 회전 방향이 나선형 흐름으로 바뀌어 하류방향으로 주 흐름에 중첩하여 발생하는 이차류로 인해 하도가 불안정해지고 내 외측의 수위차가 발생하는 편수위가 발생하면서 하도 바깥쪽으로 수위가 상승하는 현상이 나타나게 된다. 따라서 집중호우로 인해 하천에서 발생하는 재해는 주로 만곡부를 중심으로 발생하게 된다. 본 연구에서는 이와 같은 만곡부의 외측부에서 발생하는 수위상승으로 인해 제방의 월류 피해와 이차류로 인한 침식피해를 유발하게 되는 문제를 사전에 예측하기 위하여 $90^{\circ}$ 실험하도와 $180^{\circ}$ Sharp 실험하도에 2차원 유한요소 모형인 RAMS 모형을 적용하여 수리특성을 살펴보았으며, 모의 결과에 대한 정확도를 살펴보기 위해 실측자료와 비교 검토하였다. 이와 같은 연구결과는 만곡부에서 발생가능한 제방침식이나 월류로 인한 하천에서의 피해 방지에 크게 기여할 것으로 기대된다.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.31-33
• /
• 2008

산업사회에서의 전력공급 계통은 설비고장이 발생할 경우 해당지역에 국한되어 정전이 발생하기 때문에 피해가 확산되거나 사회적인 이슈가 되지는 않았다. 광케이블을 이용한 정보통신사회가 구축되어 금융과 언론을 비롯한 대부분의 생활이 인터넷을 중심으로 진행되고 있고 향후 지식기반 사회로의 진전이 급속히 진전될 것에 대비하여 전력계통 설비와 운영 방법의 고도화가 필요하게 되었다. 전력IT는 현재의 전력설비와 네트워크, IT를 이용하여 더욱 심층적인 연구가 진행되고 있으며 본 논문에서는 전력IT 연구과제 결과물의 활용성을 높이고 기술개발 과정에서의 시행착오를 최소화하기 위해 총 10개 과제를 하나로 운영할 경우를 상정하여 연구에 필요한 기술체계 모형을 개발하였고 이 모형을 토대로 향후 분산형 전원을 포함한 전력계통의 최적운영과 고장예측기법을 이용한 설비관리로 정전을 예방하여 최고품질의 전력을 공급하는데 기여하고자 하였다. 이 논문은 전력IT의 도입배경과 현재까지의 연구 성과분석을 토대로 실 계통 검증 5단계와 기술체계 모형 그리고 통합운영시스템 개념도 제시 순으로 작성하였다.

• Proceedings of the KOR-KST Conference
• /
• 1998.10a
• /
• pp.41-41
• /
• 1998

ITS틀 내의 한 분야인 도로교통정보체계 (ATIS: Advanced Traveler Information system)는 실시간 교통정보를 운전자에게 직접 제공하는 것으로서, 이를 위해 매 순간마다 가로망에 배정되는 교통량 및 통행시간을 예측할 수 있는 범용의 동적 통행배정모형(dynamic route choice model)의 개발이 필히 수반되어야 한다. 본 연구에서는 ITS사업에서 필수적으로 수반되어야 할 최적 제어이론에 의한 동적 통행 배정모형을 ATIS의 핵심 소프트웨어로 응용하기 위해 기존 연구성과를 발판으로, 순간 동적 통행 배정모형(Ran, Boyce &LeBlanc, 1993)의 통행제약조건인 링크통행함수, 특히, 과부하 시 엘켈릭의 일반식의 파라메터를 조정, 적용하여, 서울시 강남지역의 실제 가로망의 사례연구를 통해 지체식의 각각의 파라메터에 따른 결과를 O/D에 따른 통행시간, 링크통행시간, 혼잡도를 중심으로 비교 평가하여, ATIS의 핵심 소프트웨어로서 순간 동적 통행배정을 통해 보다 현실여건을 잘 반영할 수 있는 링크 통행 성능 함수를 도출하였다.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.47-56
• /
• 2008

Generally, accident exposure at intersections is relatively higher than that at roadway segments due to more possibility of merging, diverging, turning, crossing, and weaving maneuver. Furthermore, the traffic accident rate at intersections has been rapidly increasing since 1990's. Since there is more opportunity of conflict at unsignalized intersection, frequency and severity of traffic accident are more severe than signalized intersections. The purpose of the study is to analyze factors causing vehicle crashes and provide intersection design guidelines to improve intersection safety. For this study, vehicle to vehicle crash data of 116 rural 3 legs unsignalized were collected and field surveys were conducted for traffic and geometric conditions. Ordered probit models were developed to analyze the severity of crashes. It was found that weather, obstacles in minor roadsides, presence of major exclusive right lane, presence of major road crosswalk, difference between posted speed of major road and minor road, land-use around intersections, shoulder width of major road, ADT of major road are significant factors for intersection safety.

• 한국노년학
• /
• v.32 no.4
• /
• pp.1063-1086
• /
• 2012

The purpose of this study is to understand the current state of the older people's social exclusion by identifying patterns of the change in social exclusion level through a longitudinal analysis with an aim of exploring the predictors of changes. To this end, this study has adopted the panel data, the English longitudinal Study of Ageing(ELSA). The data of 7631 respondents who aged over 50 were used for the final analysis. The social exclusion of the older people was analyzed into five different sub-dimensions: social relationship; cultural activities; access to health services; financial security; and sense of loneliness. The person-centered approach that focuses on the various patterns of the trajectories of change has used semi-parametric group based model in order to estimate different trajectories among individuals. The data was analyzed using Spss 18.0 and SAS 9.2 proc traj. In results, First, semi-parametric group-based model analysis has shown that the older people are not 'homogeneous' group with similar exclusion level in every individual with same trajectories of change, but can be divided into various categories with diverse intercept and slope. Second, different trajectories in change of exclusion level help to confirm that the older people's social exclusion level increases gradually over time or remains unchanged. Third, this analysis has provided the useful guidelines to identify the high-risk groups of social exclusion. Forth, the variables that make difference in more than three dimensions include gender, age, self-perceived health, physical activity, weekly income, marital status, family relation, and beneficiary status. Implications and further suggestion were discussed.