인구통계특성 기반 디지털 마케팅을 위한 클릭스트림 빅데이터 마이닝

박지애(Jiae Park),조윤호(Yoonho Cho) 한국지능정보시스템학회 2016 지능정보연구 Vol.22 No.3

The demographics of Internet users are the most basic and important sources for target marketing or personalized advertisements on the digital marketing channels which include email, mobile, and social media. However, it gradually has become difficult to collect the demographics of Internet users because their activities are anonymous in many cases. Although the marketing department is able to get the demographics using online or offline surveys, these approaches are very expensive, long processes, and likely to include false statements. Clickstream data is the recording an Internet user leaves behind while visiting websites. As the user clicks anywhere in the webpage, the activity is logged in semi-structured website log files. Such data allows us to see what pages users visited, how long they stayed there, how often they visited, when they usually visited, which site they prefer, what keywords they used to find the site, whether they purchased any, and so forth. For such a reason, some researchers tried to guess the demographics of Internet users by using their clickstream data. They derived various independent variables likely to be correlated to the demographics. The variables include search keyword, frequency and intensity for time, day and month, variety of websites visited, text information for web pages visited, etc. The demographic attributes to predict are also diverse according to the paper, and cover gender, age, job, location, income, education, marital status, presence of children. A variety of data mining methods, such as LSA, SVM, decision tree, neural network, logistic regression, and k-nearest neighbors, were used for prediction model building. However, this research has not yet identified which data mining method is appropriate to predict each demographic variable. Moreover, it is required to review independent variables studied so far and combine them as needed, and evaluate them for building the best prediction model. The objective of this study is to choose clickstream attributes mostly likely to be correlated to the demographics from the results of previous research, and then to identify which data mining method is fitting to predict each demographic attribute. Among the demographic attributes, this paper focus on predicting gender, age, marital status, residence, and job. And from the results of previous research, 64 clickstream attributes are applied to predict the demographic attributes. The overall process of predictive model building is compose of 4 steps. In the first step, we create user profiles which include 64 clickstream attributes and 5 demographic attributes. The second step performs the dimension reduction of clickstream variables to solve the curse of dimensionality and overfitting problem. We utilize three approaches which are based on decision tree, PCA, and cluster analysis. We build alternative predictive models for each demographic variable in the third step. SVM, neural network, and logistic regression are used for modeling. The last step evaluates the alternative models in view of model accuracy and selects the best model. For the experiments, we used clickstream data which represents 5 demographics and 16,962,705 online activities for 5,000 Internet users. IBM SPSS Modeler 17.0 was used for our prediction process, and the 5-fold cross validation was conducted to enhance the reliability of our experiments. As the experimental results, we can verify that there are a specific data mining method well-suited for each demographic variable. For example, age prediction is best performed when using the decision tree based dimension reduction and neural network whereas the prediction of gender and marital status is the most accurate by applying SVM without dimension reduction. We conclude that the online behaviors of the Internet users, captured from the clickstream data analysis, could be well used to predict their demographics, thereby being utilized to the digital marketing.

Demographic data is more predictive of component size than digital radiographic templating in total knee arthroplasty

Wallace Stephen J.,Murphy Michael P.,Schiffman Corey J.,Hopkinson William J.,Brown Nicholas M. 대한슬관절학회 2020 대한슬관절학회지 Vol.32 No.-

Preoperative radiographic templating for total knee arthroplasty (TKA) has been shown to be inaccurate. Patient demographic data, such as gender, height, weight, age, and race, may be more predictive of implanted component size in TKA.A multivariate linear regression model was designed to predict implanted femoral and tibial component size using demographic data along a consecutive series of 201 patients undergoing index TKA. Traditional, two-dimensional, radiographic templating was compared to demographic-based regression predictions on a prospective 181 consecutive patients undergoing index TKA in their ability to accurately predict intraoperative implanted sizes. Surgeons were blinded of any predictions. Patient gender, height, weight, age, and ethnicity/race were predictive of implanted TKA component size. The regression model more accurately predicted implanted component size compared to radiographically templated sizes for both the femoral ( P = 0.04) and tibial ( P < 0.01) components. The regression model exactly predicted femoral and tibial component sizes in 43.7 and 43.7% of cases, was within one size 90.1 and 95.6% of the time, and was within two sizes in every case. Radiographic templating exactly predicted 35.4 and 36.5% of cases, was within one size 86.2 and 85.1% of the time, and varied up to four sizes for both the femoral and tibial components. The regression model averaged within 0.66 and 0.61 sizes, versus 0.81 and 0.81 sizes for radiographic templating for femoral and tibial components. A demographic-based regression model was created based on patient-specific demographic data to predict femoral and tibial TKA component sizes. In a prospective patient series, the regression model more accurately and precisely predicted implanted component sizes compared to radiographic templating.Prospective cohort, level II.

인구통계학적 요인 및 원격검침 자료를 활용한 가정용 물 사용패턴 분류 및 물 사용량 예측 연구

김기범,구자용,박해금,김태현,형진석 대한상하수도학회 2022 상하수도학회지 Vol.36 No.3

The water consumption data of individual consumers must be analyzed and forecast to establish an effective water demand management plan. A k-mean cluster model that can monitor water use characteristics based on hourly water consumption data measured using automated meter reading devices and demographic factors is developed in this study. In addition, the quantification model that can estimate the daily water consumption is developed. K-mean cluster analysis based on the four clusters shows that the average silhouette coefficient is 0.63, also the silhouette coefficients of each cluster exceed 0.60, thereby verifying the high reliability of the cluster analysis. Furthermore, the clusters are clearly classified based on water usage and water usage patterns. The correlation coefficients of four quantification models for estimating water consumption exceed 0.74, confirming that the models can accurately simulate the investigated demographic data. The statistical significance of the models is considered reasonable, hence, they are applicable to the actual field. Because the use of automated smart water meters has become increasingly popular in recent year, water consumption has been metered remotely in many areas. The proposed methodology and the results obtained in this study are expected to facilitate improvements in the usability of smart water meters in the future.

Characteristics of Private Label Users of Low Involvement Products : : Scanner Data Analysis

Jae-Wun CHO(조재운) 한국유통과학회 2019 유통과학연구 Vol.17 No.5

Purpose - The purpose of the research is to identify the demographic characteristics of the customers with high private label purchase intention. According to the previous research demographics such as gender, age, income, and residence type affect private label purchase intention indirectly through psychographics rather than directly. For instance, higher income group is time pressured, price-insensitive, quality-sensitive, less likely to enjoy shopping utilitarian products, and less likely to be variety-seeking. The main contribution of this research is to verify the results found in the previous empirical foreign research using scanner data and to investigate the differences of the characteristics of private label users between Korea and the foreign countries. Research design, data, and methodology - In order to empirically test the proposed hypotheses, scanner data of a Korean major super center was analyzed. Results - Empirical results show that private labels are more favored by old people over 50s, dwellers in individual house, lower income group, and frequent store visitors. Age of 30s, dwellers in the apartment of 30 pyung, higher income group, and consumers who purchased a large amount are less likely to purchase private labels. Gender turned out not to affect private label purchase. It should be noted that there is a significant multicollinearity among independent variables. Conclusions - The research findings provide managerial implication for retailers’ private label strategy. In general, retailers heavily send private label coupons to the customers with high purchase volume. According to the research, however, store visit frequency is much more positively associated with private label purchase than purchase amount. The study has some limitations. The samples are only consumers with private label purchase experience. The data were drawn from one store and only 8 commodity products were used for the analysis. Also, if more demographics were availabl

한국 종교소수자의 현황과 문제점 -인구센서스와 해외 데이터베이스의 비교-

유광석 ( Kwang Suk Yoo ) 한국사회역사학회 2015 담론 201 Vol.18 No.2

이 논문은 국내 종교연구자들이 인구센서스의 결과에 대한 일종의 신념을 소유하고 있음을 보여준다. 그들은 종교에 관한 인구센서스 결과에 대해 합리적 의심을 전제하기보다 오히려 그들 주장의 신뢰 가능한 유일한 증거로서 의존하는 경향이있다. 하지만, 1985년, 1995년, 2005년 한국의 인구센서스는 종교연구자들에 의해 가장 빈번하게 인용되는 주요한 국제적 데이터베이스들과는 극단적으로 상이한 종교인구분포를 보여주고 있다. Pew Database, World Christian Database,World Values Survey Database, 그리고 Association of Religion DataArchives와 같은 국제적 데이터베이스들은 공통적으로 한국인들과 한국종교 연구자들 모두에게 매우 낯선 종교적 풍경을 제시하고 있다. 그들의 종교적 범주와 조사방법이 서구적이고 기독교적인 관점에 기초한 것임에도 불구하고, 그들의 자료는 전 세계의 다양한 종교와 사회에 대한 포괄적 이해를 제공하는 가장 신뢰할 만한자료들로서 일반적으로 인정되고 있다. 한국적 종교성에 부합하는 좀 더 세밀하고 전문화된 사회조사가 우리에게 없는 현실에서 이처럼 거대한 해외데이터베이스들의 한국적 종교성에 대한 왜곡과 오류를 바로잡기는 쉽지 않다. 따라서 본 연구는 사회적 문제들에 대한 강력한 예측 변수로서 종교의 영향력을 정확히 파악하기 위해 인구센서스가 아니라 한국의 종교단체 또는 종교인들에 제한된 종교전수조사(religious census)를 정부가 조속히 실시할 필요가 있다고 주장한다. This paper argues that domestic scholars of religious studies have a kind of faith in the results of demographic census. They do not tend to put any rational doubt upon the census results, and thereby utilize them as the only and reliable evidence of their arguments. However, demographic census is likely tooversimplify a very complicated religious variables within a few categories because it is not designed for understanding and analyzing a religious situation of respondents. The 1985, 1995, and 2005 demographic census by Statistics Korea reveals a religious distribution greatly different from major international databases cited frequently by scholars of religious studies. The Pew Database, World Christian Database, World Values Survey Database, and the Association of Religion Data Archives all display a Korean religious landscape which is alien to Koreans and even to scholars of Korean religions. Although their categories are based on the western and christian perspectives, they are usually considered as one of the most reliable databases, which provide researchers of religion with a comprehensive understanding of distant societies and their religion. Given no detailed surveys specific in Korean religiosity, it is not easy to correct any errors and even distortions of the giant international databases concerning a Korean religiosity. For this reason, scholars of Korean religions need to prompt Korean government to conduct the historically first religious census or large-scale social surveys of religions.

패널자료 분석을 이용한 중,고령자 단독가계의 의료비지출 영향 요인

윤정혜 ( Jung Hai Yoon ),김시월 ( Si Wuel Kim ),장윤희 ( Yun Hee Chang ),조향숙 ( Hyang Sook Cho ),송현주 ( Hyun Ju Song ) 한국소비자학회 2010 소비자학연구 Vol.21 No.4

이 연구는 국민노후보장패널조사(KReIS)의 l-3차년 자료를 이용하여, 중·고령자 단독가계의 의료비지출규모와 의료비지출비중 추이에 가구주의 소득, 건강상태 및 기타 인구사회학적 특성의 변화가 미치는 영향을 분석하였다. 1차년도 (2005년) 조사 당시 50세 이상 단독가계의 가구주로서 2차년도(2007년), 3차년도(2009년) 조사에도 결측값 없이 응답한 중·고령자 단독가구주 683명 1.794건의 패널자료가 분석에 사용되었다. 의료비지출의 선형회귀모형을 OLS, 개인고정효과 및 개인랜덤효과 모형으로 분석한 결과는 다음과 같다. 첫째, 의료비 소비는 정상재이며 필수재의 성격을 보인다. 둘째, 증·고령자 단독가계의 의료비지출규모는 질환이나 장애가 있을 경우, 연령이 높을수록 증가하였으며, 이것은 건강상태가 의료비지출에 주요한 영향요인임을 알 수 있다. 셋째, 조사시점이 최근으로 올수록 의료비지출규모가 감소하였는데, 이는 2008난 7월에 시행된 노인장기요양보험과 2008년 경제위기로 인한 소비지출의 위축이 원인이 되었을 것으로 보인다. 넷째, 교육수준이 높을 경우 의료비지출비중이 낮은 것으로 보아 교육을 통한 인적자본이 의료비지출의 중요한 영향요인임을 알 수 있다. 다섯째, 여성은 남성에 비해 전반적으로 의료비지출규모가 크며, 남성은 의료비지출의 소득탄력성이 여성에 비해 훨씬 높을 뿐 아니라 질환이나 연령에 따른 효과도 여성에 비해 더 뚜렷했다. 여섯째, 자산, 부채, 취업 등의 경제적 지위도 의료비지출과 유의한 관련을 보이나 이것은 인과관계라기보다는 내생성으로 인한 상관관계인 것으로 보인다. 이러한 연구결과는 저소득층 중·고령자 단독가계 가구주를 위한 질병 예방, 치료 및 의료비 지출절감정책, 질환이 있는 중·고령자 단독가계 가구주를 위한 치료 및 의료비 지출절감정책, 예비노인기부터 건강관리 및 질병예방 지원정책, 저교육 수준의 중·고령자 단독가계 가구주를 위한 청·장년기부터의 건강관리와 질병예방교육 프로그램, 여성가구주 전체와 특히 저소득층 남성가구주를 위한 의료비지출절감정책이 필요함을 시사한다. Korea is approaching an aged society faster than most OECD countries. By 2014, the 65 and older population will account for 14 percent of the population. In 2005, every fifth Korean household was a single-person household mainly due to the elderly living alone. The elderly are facing many problems today, but healthcare and economic hardship are their utmost concern. This study uses the 2005, 2007 and 2009 surveys of the Korean Retirement and Income Study (KReIS) to explore how income, health status, and socio-demographic characteristics determine health care expenditures among older Koreans in single-person households. This study is different from previous studies in several aspects: first, it takes advantage of panel data analysis: second, the sample includes the near elderly, which age group is identified as significant consumers of health care: and third, it adds to the literature by contrasting men against women as health care consumers. The sample consisted of 1.794 observations from 683 single householders aged 50 years or older in 2005. Both the size and share of health care expenditures, the latter of which was defined as a fraction of total consumption expenditures, were regressed on income, health status, and other socio-demographic characteristics of the household. The socio-demographic variables were selected based on the literature and included age, gender, cohort, education, area of residence, assets, debts, home ownership, employment status, health insurance coverage, and receipt of other social insurance and welfare benefits. Regression coefficients were obtained through Ordinary Least Squares (OLS), individual fixed effects, and random effects models. The main findings can be summarized as the following: First, in all models income is positively associated with health care expenditures, with the fixed-effect income elasticity at 0.14, suggesting that health care consumption is a normal good and necessary. Second, having disease or disability is positively associated with both the size and the share of health care expenditures. In addition, after controlling for the survey year and birth cohort, older age is positively associated with the size of health care expenditure. This suggests that health status is a significant predictor of health care expenditures. Third, the size of health care expenditures has decreased over the 2005-2009 period. It can be inferred that macroeconomic and institutional factors like nationwide expansion of long-term care insurance in 2008, and economic recession during the late 2000`s played a role in reducing health care expenditures by the elderly. Fourth, education is negatively associated with the share of health care expenditures as a fraction of total consumption expenditures of the household. This appears to suggest that human capital plays a role in reducing the need for health care expenditure at an older age. Fifth, when income, health status, and other socio-demographic characteristics were controlled, women spend significantly more on health care than men. This gender difference is robust in both dependent variables-the size as well as the share of health care expenditures. Income elasticity of health care expenditures is also much greater for men than for women. Furthermore, health care expenditures by men vary more markedly by age and health status compared to those by women. Sixth, economic status such as assets, debt, and employment status are also significant, most likely due to endogeneity arising from inherent healthiness. Findings from this study offer several policy implications. First, it is suggests that the health care policy for the older single-person households target low-income households in all phases of prevention, treatment, and cost reduction. Second, such policy should particularly focus on the older single-person households who have disease or disability. Third, it is important to provide support for disease prevention before the individuals reach old age and develop educational programs on health management and disease prevention for the middle-age population. Fourth, this study suggests that policies that aim to reduce health care costs should be genderspecific. Such policies should be directed at older women in general and older men especially in low-income households.

저관여 생필품 소매업체상표 구매자의 특성: 스캐너 데이터 분석

조재운 한국유통과학회 2019 유통과학연구 Vol.17 No.5

Purpose - The purpose of the research is to identify the demographic characteristics of the customers with high private label purchase intention. According to the previous research demographics such as gender, age, income, and residence type affect private label purchase intention indirectly through psychographics rather than directly. For instance, higher income group is time pressured, price-insensitive, quality-sensitive, less likely to enjoy shopping utilitarian products, and less likely to be variety-seeking. The main contribution of this research is to verify the results found in the previous empirical foreign research using scanner data and to investigate the differences of the characteristics of private label users between Korea and the foreign countries. Research design, data, and methodology - In order to empirically test the proposed hypotheses, scanner data of a Korean major super center was analyzed. Results - Empirical results show that private labels are more favored by old people over 50s, dwellers in individual house, lower income group, and frequent store visitors. Age of 30s, dwellers in the apartment of 30 pyung, higher income group, and consumers who purchased a large amount are less likely to purchase private labels. Gender turned out not to affect private label purchase. It should be noted that there is a significant multicollinearity among independent variables. Conclusions - The research findings provide managerial implication for retailers’ private label strategy. In general, retailers heavily send private label coupons to the customers with high purchase volume. According to the research, however, store visit frequency is much more positively associated with private label purchase than purchase amount. The study has some limitations. The samples are only consumers with private label purchase experience. The data were drawn from one store and only 8 commodity products were used for the analysis. Also, if more demographics were available, a more complete description on the private brand users’ profile could have been derived. We propose the following future research. Research using the data including consumers without private label experience, research investigating direction of causality between private label loyalty and store loyalty, and research using hedonic private label products such as TV and PC could be promising.

Assessment of P values for demographic data in randomized controlled trials

안은진,김종해,김태균,박재홍,이동규,이상석,인준용,강현 대한마취통증의학회 2019 Korean Journal of Anesthesiology Vol.72 No.2

monly reported in table 1 of the article for the purpose of emphasizing the lack of differences between or among groups. As such, the authors intend to demonstrate that statistically insignificant P values in the demographic data confirm that group randomization was adequately performed. However, statistically insignificant P values do not necessarily reflect successful randomization. It is more important to rigorously establish a plan for statistical analysis during the design and planning stage of the study, and to consider whether any of the variables included in the demographic data could potentially affect the research results. If a researcher rigorously designed and planned a study, and performed it accordingly, the conclusions drawn from the results would not be influenced by P values, regardless of whether they were significant. In contrasts, imbalanced variables could affect the results after variance controlling, even though whole study process are well planned and executed. In this situation, the researcher can provide results with both the initial method and a second stage of analysis including such variables. Otherwise, for brief conclusions, it would be pointless to report P values in a table simply listing baseline data of the participants.

환자 의료 정보 공유 및 데이터 통합을 위한 데모그래픽 데이터 활용 연구

임종우(Jongwoo Lim),정은영(Eun-Young Jung),정병희(Byoung-Hui Jeong),박동균(Dong Kyun Park),황보 택근(Taeg-keun Whangbo) 대한전자공학회 2014 전자공학회논문지 Vol.51 No.10

온라인에서 공유 및 활용되고 있는 정보들이 기하급수적으로 생성되는 인터넷 정보 시대에서, 개별 의료기관의 환자 정보는 의료기관 고유의 데이터베이스 구성 및 환자 사생활 정보 보호 문제 등의 이유로 인해 병원들 간의 환자 데이터 공유가 원활히 이루어지지 않고 있다. 환자 사생활 정보를 보호하면서 각 의료기관 고유의 환자 정보를 의료기관들 간에 상호 공유하는 것은 의료 정보화를 위해 아직도 해결해야 할 과제로 남아있다. 본 논문에서는 환자 사생활 정보를 보호하면서 환자의 의료정보를 공유하기 위해서, 국내외 의료정보 공유 현황 및 관련 국제 의료정보 표준안을 고찰 및 국내 의료기관의 데모그래픽 데이터를 활용하기 위해 실제 국내 의료기관의 환자 데이터 구조 및 특성을 분석하고 의료 정보 공유 시스템 구조 설계를 제안하고 자 한다. Recently, although exponentially growing the quantity of information that have been used and shared on internet networks, the patient information of each medical center have not been used and shared among medical centers due to the protection of patients privacy and the different database schema. To address this problem, we have studied the data structure of the patient information, the standard of medical information for patients we propose a patient information sharing system design that each medical center is able to use and share the patient information among medical centers in spite of different patient information systems with protecting patients privacy.

Multiple Myeloma: a Retrospective Analysis of 61 Patients from a Tertiary Care Center

Sultan, Sadia,Irfan, Syed Mohammed,Parveen, Saira,Ali, Hamza,Basharat, Maria Asian Pacific Journal of Cancer Prevention 2016 Asian Pacific journal of cancer prevention Vol.17 No.4

Background: Multiple myeloma (MM) is an acquired clonal B-cell malignancy which primarily affects elderly individuals with an annual incidence of approximately 1% of all malignancies. Our aim is to study demographic and clinicopathological features of adult Pakistani MM patients at presentation. Materials and Methods: This single centre retrospective study extended from January 2010 to December 2014. Data were retrieved from the patients' maintained records on predetermined performa. Results: Overall, 61 patients were diagnosed at our institution with MM during the study period. There were 43 males and 18 females. Age ranged between 34 and 81 years with a mean of $56.1{\pm}12.8$ and a median of 57 years. The male to female ratio was ~2:1. Common presenting complaints included fatigue (81.9%), backache (80.3%) and bone pain (67.2%). Physical findings revealed pallor (44.2%) as a presenting clinical feature. The mean hemoglobin value was $8.9{\pm}1.7g/dl$ with a mean MCV of $85.3{\pm}11.0fl$. Severe anemia with hemoglobin <8.5 gm/dl was seen in 40.9%. The mean total leukocyte count was $8.9{\pm}8.2{\times}10^9/l$, the ANC was $5.0{\pm}3.1{\times}10^9/l$ and the mean platelet count was $188.4{\pm}150.6{\times}10^9/l$. Conclusions: MM in Pakistani patients is seen in a relatively young population with male preponderance. The majority of patients present with symptomatic anemia and backache to seek medical attention. However, clinico-pathological features appear comparable to the published literature.