수사기법으로서의 데이터 마이닝에 대한 법적 고찰

양종모(Yang Jongmo) 대검찰청 2013 형사법의 신동향 Vol.0 No.40

현대사회는 엄청난 정보가 생성되고 축적되는 소위 정보화 사회라고 할 수 있다. 모바일 폰 등 획기적인 정보 인프라로 인해 빅데이터가 출현하고, 이러한 빅데이터로부터 가치 있는 정보를 찾아내는 데이터 마이닝 기법도 등장하게 되었다. 이러한 데이터 마이닝기법은 아주 다양하게 쓰이지만 수사에 있어서도 그 유용성이 크다. 국내에서는 아직 이러한 데이터 마이닝을 수사에 활용한 실례를 찾아보기 어렵지만 조만간 수사에 데이터 마이닝 기법을 도입할 것으로 보고 그에 대한 법적 규제를 논하여 보았다. 데이터 마이닝은 새로운 형태의 강제처분이다. 그 과정에서 사생활 영역 침해가 당연히 수반되기 때문인데, 기존의 압수 ‧ 수색과 유사한 측면이 있지만 기존의 강제처분에 대한 규제로는 도저히 해결할 수 없는 특성도 가지고 있다. 이를 규제할 수 있는 새로운 방안과 그에 기초한 규정의 신설이 필요하겠지만, 현행 법제를 전제로 그 법적 규제에 대하여 검토하였다. 사생활 영역 침해의 심각성 때문에 데이터 마이닝이나 그 전제가 되는 정보의 수집에 영장주의가 적용되어야 하고, 개인의 동의가 없거나 법원의 영장을 발부받지 않고 행하는 데이터 마이닝은 위법하다고 볼 여지가 없지 않지만, 데이터 마이닝 자체는 영장주의에 적합하지 않고, 그 필요성에 비추어 그것을 규제할 수 있는 새로운 규정의 신설 이전이라도 수사 활동의 일환으로 허용되어야 하고, 그 결과를 이용한 수사도 적법하다고 할 것이다. 다만 데이터 마이닝의 결과는 신뢰도 측면에서 문제가 있어 그 결과를 직접 증거로 쓰기는 어렵다고 할 것이다. Data mining technology allows large volumes of data to be exploited for discovering previously unknown, possibly useful information and knowledge. This is due to the improvement in the database technology which has provided large data and our high dependence on internet which results in mass data production. More specifically, data mining is the application of database technology and techniques-such as statistical analysis and modeling-to uncover hidden patterns and subtle relationships in data and to infer rules that enable the prediction of future results. Data mining application plays an important role in various fields. Even the government has been using data mining techniques for various purposes, from attempting to improve service to trying to detect terrorist patterns and activities. Indeed, several departments and agencies are using or planning to use data mining. Efforts to detect criminal activities and patterns are spread out somewhat evenly across agencies. Since 9/11, The U.S. government agency have been eager to experiment with data mining process as a way of nabbing criminals. However, the privacy of personally sensitive information is not respected generally in the process, which creates some legal problems. People have worried about improper data use in data mining process, especially arbitrary invasions of personal privacy by government officials. In this study, the emerging legal issues of data mining are explored and the admissibility of evidence obtained by data mining is presented. It considers the various arguments for privacy concerns relating data mining. If data mining performed without a proper search warrant, the evidence obtained in the process is illegal and may not be used in court? It is not always true. Under certain circumstances, such evidence is admissible in court. Data mining is new type of compulsory execution and in the permissible scope of warrantless search under various circumstances. The existing law governing the warrant process is not suitable for data mining process. So this article also urges legislatures to update statutory rule that govern the warrant process in response to the new challenge of data mining and argues that data mining will trigger the need for a new criminal procedure to regulate its process in criminal investigation.

발생 간격 기반 가중치 부여 기법을 활용한 데이터 스트림에서 가중치 순차패턴 탐색

장중혁(Joong Hyuk Chang) 한국지능정보시스템학회 2010 지능정보연구 Vol.16 No.3

Sequential pattern mining aims to discover interesting sequential patterns in a sequence database, and it is one of the essential data mining tasks widely used in various application fields such as Web access pattern analysis, customer purchase pattern analysis, and DNA sequence analysis. In general sequential pattern mining, only the generation order of data element in a sequence is considered, so that it can easily find simple sequential patterns, but has a limit to find more interesting sequential patterns being widely used in real world applications. One of the essential research topics to compensate the limit is a topic of weighted sequential pattern mining. In weighted sequential pattern mining, not only the generation order of data element but also its weight is considered to get more interesting sequential patterns. In recent, data has been increasingly taking the form of continuous data streams rather than finite stored data sets in various application fields, the database research community has begun focusing its attention on processing over data streams. The data stream is a massive unbounded sequence of data elements continuously generated at a rapid rate. In data stream processing, each data element should be examined at most once to analyze the data stream, and the memory usage for data stream analysis should be restricted finitely although new data elements are continuously generated in a data stream. Moreover, newly generated data elements should be processed as fast as possible to produce the up-to-date analysis result of a data stream, so that it can be instantly utilized upon request. To satisfy these requirements, data stream processing sacrifices the correctness of its analysis result by allowing some error. Considering the changes in the form of data generated in real world application fields, many researches have been actively performed to find various kinds of knowledgeembedded in data streams. They mainly focus on efficient mining of frequent itemsets and sequential patterns over data streams, which have been proven to be useful in conventional data mining for a finite data set. In addition, mining algorithms have also been proposed to efficiently reflect the changes of data streams over time into their mining results. However, they have been targeting on finding naively interesting patterns such as frequent patterns and simple sequential patterns, which are found intuitively, taking no interest in mining novel interesting patterns that express the characteristics of target data streams better. Therefore, it can be a valuable research topic in the field of mining data streams to define novel interesting patterns and develop a mining method finding the novel patterns, which will be effectively used to analyze recent data streams. This paper proposes a gap-based weighting approach for a sequential pattern and amining method of weighted sequential patterns over sequence data streams via the weighting approach. A gap-based weight of a sequential pattern can be computed from the gaps of data elements in the sequential pattern without any pre-defined weight information. That is, in the approach, the gaps of data elements in each sequential pattern as well as their generation orders are used to get the weight of the sequential pattern, therefore it can help to get more interesting and useful sequential patterns. Recently most of computer application fields generate data as a form of data streams rather than a finite data set. Considering the change of data, the proposed method is mainly focus on sequence data streams.

Data Outsourcing based on Secure Association Rule Mining Processes

V. Sujatha,Debnath Bhattacharyya,P. Silpa Chaitanya,Tai-hoon Kim 보안공학연구지원센터 2015 International Journal of Security and Its Applicat Vol.9 No.3

Data mining is the process of extracting information from data warehousing applications. Data outsourcing is the major task in present days, for accessing services and other features of the database processing. But sometimes this process may achieve to split among various parties with recommended data items in analyzing of the data. Data security is one of the key processes in outsourcing data to various outside users. Traditionally Fast Distribution Mining algorithm was proposed for securing distributed data. This paper addresses a problem by secure association rules over partitioned data in both horizontal and vertical representation. A secure frequency developed algorithm is used for doing above process efficiently in partitioned data, which includes services of the data in outsourcing process. Frequent item sets are used to access services in outsourcing data in recent application development data mining. Our proposed work maintains efficient security over vertical and horizontal view of representation in secure mining applications. The result shows that algorithm timing is desirable for big size data for security considerations using association rule mining operations in real time application development.

Stream Data Mining: Platforms, Algorithms, Performance Evaluators and Research Trends

Bakshi Rohit Prasad,Sonali Agarwal 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.9

Streaming data are potentially infinite sequence of incoming data at very high speed and may evolve over the time. This causes several challenges in mining large scale high speed data streams in real time. Hence, this field has gained a lot of attention of researchers in previous years. This paper discusses various challenges associated with mining such data streams. Several available stream data mining algorithms of classification and clustering are specified along with their key features and significance. Also, the significant performance evaluation measures relevant in streaming data classification and clustering are explained and their comparative significance is discussed. The paper illustrates various streaming data computation platforms that are developed and discusses each of them chronologically along with their major capabilities. This paper clearly specifies the potential research directions open in high speed large scale data stream mining from algorithmic, evolving nature and performance evaluation measurement point of view. Finally, Massive Online Analysis (MOA) framework is used as a use case to show the result of key streaming data classification and clustering algorithms on the sample benchmark dataset and their performances are critically compared and analyzed based on the performance evaluation parameters specific to streaming data mining.

빅데이터의 이용활성화를 위한 저작권법적 고찰 - 데이터 마이닝 등을 중심으로 -

최종모 ( Choi Jongmo ) 중앙대학교 문화미디어엔터테인먼트법연구소 2018 문화.미디어.엔터테인먼트 법 Vol.12 No.2

제4차 산업혁명은 빅데이터 및 인공지능 등을 원동력으로 삼아 발전되며, 인공지능은 빅데이터와 데이터 마이닝을 통하여 발전된다. 데이터는 정형데이터와 비정형데이터로 나눌 수 있으며, 특히 비정형데이터의 경우 저작권법적 쟁점이 발생한다. 데이터 마이닝시 일시적 복제 등이 발생한다. 또한 데이터 마이닝이 현행저작권법 저작재산군재한사유로서 별도의 규정으로 규정되어 있지 않다. 그러나 데이터 마이닝이 비영리를 목적으로 하는 경우에는 저작권법 제35조의3에 따른 공정이용에 해당될 여지가 높다고 판단되고, 영리목적인 경우 그러하지 않다. 이러한 쟁점에 대한 해결방안으로서 영리목적을 포함한 데이터 마이닝을 저작재산권제한사유로 신설하는 것을 제시한다. 비영리목적인 데이터 마이닝만을 저작재산권제한사유로 신설하는 경우 데이터 마이닝 관련 산업을 육성 및 촉진하는데 장애요인이 될 것으로 판단된다. 다만 저작재산권제한사유로서 데이터 마이닝에 대한 규정의 신설로 인하여 발생하는 저작재산권자의 재산권의 침해는 ‘정보 분석(데이터 마이닝)의 목적을 위한 보상금’제도를 신설함으로써 보호되어야 한다. 이러한 데이터 마이닝이 저작재산권제한사유로서 신설되면, 일시적 복재의 경우 합법적인 저작물을 이용한 경우에는 저작권침해에 해당되지 않는다. 수집데이터로서 인공지능 작성물을 활용한 경우 현행 저작권법상 인공지능 작성물을 저작권법상 저작물에 해당되지는 않으나, 인공지능 작성물에 대한 저작권법상 보호에 대한 논의가 제기될 것으로 판단된다. 또한 인공지능 작성물을 보호하는 경우 인간의 창작물과 구별될 필요가 있다. The Fourth Industrial Revolution will be developed with Big data and Artificial Intelligence as the driving force. Artificial Intelligence also is developed through big data and data mining. The Data can be divided into structured data and unstructured data. The unstructured data has copyright legal issues. Moreover a temporary reproduction at data mining on unstructured data occurs. In addition, data mining falls not currently the limitation to protection of economic rights. However, if data mining is for non-profit purposes, it consider highly as applicable to fair use pursuant to Article 35-3 of the Copyright Act, but it is not for profit-making purposes. As a solution to these issues, the data mining including for-profit purposes is proposed as the limitation to protection of economic rights. If data mining, which is a nonprofit purpose, falls only under the limitation to protection of economic rights, it will be a Hurdle to fostering and promoting the industry related to data mining. However, it arise infringement on the property right of the author rights holder, if data mining, which is a profit purpose, falls under the limitation to protection of economic rights. According, the of the property right in the author rights holder should be protected by adopting of the “compensation for the purpose of information analysis (data mining)”system. In addition, in the case of a temporary reproduction, it does not constitute a copyright infringement if a legitimate work is used. If it is used a work written by Artificial Intelligence as a basic data, it is need to discuss that the work written by Artificial Intelligence should be protected by Copyright Law. although it is not currently under Copyright Law. The work written by Artificial Intelligence should be also protected different from a work written by Human.

데이터마이닝 면책 입법 방향에 대한 의문

홍승기 한국경영법률학회 2022 經營法律 Vol.32 No.4

The Korean Government is planning to allow data mining for commercial purposes by enacting an additional clause in the Copyright Act. Its necessity is questionable in that Korea has “fair use” as a general limitation clause(Article 35-5) since 2011. If commercial purposes data mining is inevitable, it can be resolved under the control of four fairness factors with the existing “fair use” clause which was adopted with the Korea/US FTA. Even before the legislation of "fair use" in 2011, Korean Courts have referred to the four fairness factors of Article 107 of the U.S. Copyright Act as an analysis tool in the application of Article 28, a pseudo general limitation clause at that time. This experience of the Courts regarding 'fair use' doctrine is by no means negligible. It is also worth noting the Australian government's attitude to introduce ‘fair use’ doctrine. The Australian ALRC analyzed that 'fair use' suggests more clear and predictable standard compared to diverse 'fair dealings' of the Australian copyright act. In Germany, data mining for non-profit academic purposes only was allowed, France limited the sphere to scientific publications from legitimate sources, so it was intended to allow only text mining. Commercial purposes data mining seems to be allowable under the European Union Digital Single Market Directive, however right holders have the right to opt-out for commercial data mining(Art. 4). The opt-out scheme may leave commercial purposes data mining at the mercy of the content owners, making EU data mining operators inferior to the U.S. competitors. The fact that U.K, recently drew a line against commercial data mining is also noticeable. Comparatively and from our experience, the 'fair use' of the Korean Copyright Act itself could function as a useful scheme in dealing with data mining, commercial purpose inclusive though which is undesirable. In this situation, additional enactment the Government is pursuing currently might result in legislative excess. 국회에 상정된 저작권법 전면 개정안에서는 상업적 목적 데이터마이닝까지 허용하였다. 우리 저작권법이 일반규정으로서의 공정이용(제35조의 5)을 이미 입법하고 있다는 점에서 그 타당성은 의문이다. 상업적 이익의 데이터마이닝이 부득이 필요하다면 기존 ‘공정이용’ 규정으로 - 4가지 공정성 항목(fairness factors)의 통제 하에 - 해결 할 수 있다. 우리 법원은 2011년 ‘공정이용’을 입법하기 훨씬 이전부터 ‘공표된 저작물의 인용(제28조)’의 적용에 있어 미국 저작권법 제107조의 4개 항목을 분석도구로 적잖이 활용하여 왔다. 법원이 분석도구로서 미국법의 ‘fair use’ 규정을 활용한 경험이 결코 무시할만한 수준이 아닌 것이다. 최근 ‘fair use’ 도입을 시도하는 호주 정부의 입장도 참고할 만하다. 호주 입법위원회(ALRC)는 ‘fair use’가 그 자체로서 호주 저작권법의 한정적 열거규정인 ‘fair dealing’과 비교할 때 명확하고 예측가능하다고 분석하였다. ‘fair use’의 4가지 공정성 항목, 호주의 판례나 관련국가의 판례, 업계의 관행, 직업규약(code of practice)을 고려하면 이용자와 권리자가 예상할 만한 기준이 도출된다는 것이다. 독일에서는 비영리학술목적의 데이터마이닝을 허용하면서 보상의무까지 규정하였고, 프랑스는 그 대상을 합법적 출처의 과학출판물로 제한하고 있으므로 텍스트마이닝만을 허용하는 취지였다. 유럽연합 디지털 단일시장 지침의 데이터마이닝 규정은 상업적 목적 데이터마이닝에 opt-out이 가능하도록 하였다. 실제로 opt-out 제도는 상업적 목적 데이터마이닝을 권리자의 처분에 맡기는 결과가 되고, 결과적으로 상업적 목적 데이터마이닝까지도 ‘fair use’로 허용할 여지가 있는 미국에 비하여 유럽의 데이터마이닝 사업자를 배려하지 않는다는 비판까지도 받는다. 유럽연합에서 이탈한 영국이 최근 창작자들의 반발을 의식하여 상업적 목적 데이터마이닝에 대하여 일정한 선을 그었다는 사실은 시사하는 바가 크다. 비교법적으로 보나 우리 법원의 경험으로 보나 저작권법의 ‘공정이용’ 규정은 그 자체로 데이터마이닝을 처리하는데 무리가 없는 규정이다. 저작권법 전면개정안의 데이터마이닝 규정은 과잉입법이라고 지적한다.

Data Mining for High Dimensional Data in Drug Discovery and Development

Lee, Kwan R.,Park, Daniel C.,Lin, Xiwu,Eslava, Sergio Korea Genome Organization 2003 Genomics & informatics Vol.1 No.2

Data mining differs primarily from traditional data analysis on an important dimension, namely the scale of the data. That is the reason why not only statistical but also computer science principles are needed to extract information from large data sets. In this paper we briefly review data mining, its characteristics, typical data mining algorithms, and potential and ongoing applications of data mining at biopharmaceutical industries. The distinguishing characteristics of data mining lie in its understandability, scalability, its problem driven nature, and its analysis of retrospective or observational data in contrast to experimentally designed data. At a high level one can identify three types of problems for which data mining is useful: description, prediction and search. Brief review of data mining algorithms include decision trees and rules, nonlinear classification methods, memory-based methods, model-based clustering, and graphical dependency models. Application areas covered are discovery compound libraries, clinical trial and disease management data, genomics and proteomics, structural databases for candidate drug compounds, and other applications of pharmaceutical relevance.

Research on Information Forecasting Based on Different Data Mining Techniques

Yiran Wang,Guang Zheng 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.10

This paper has been explored information data prediction implementation access based on data mining combination model. With data mining technology as the entry point and in combination with the analysis on information data prediction characteristics. Research on variable substitution to non-linear regression forecast model precision's influence, and seek the modeling method that can improve the forecast precision. Based on the Data mining, the transform in space and the weighted processing combined method, make full use of information that the primary data provide. Given modeling method of combination forecast model based on the Data mining. Based on Data mining’s combination forecast model’s modeling method can reduce the serious influence that the variable substitution brings and has fully used useful information in the primary data. It obviously improved the accuracy of the prediction model.

Application of Data Mining Using Artificial Neural Network : Survey

Muhammad Arif,Khubaib Amjad Alam,Mehdi Hussain 보안공학연구지원센터 2015 International Journal of Database Theory and Appli Vol.8 No.1

The use of neural network is very wide in data mining due to some characteristic like parallel performance, Self-organizing adaptive, robustness and fault tolerance. Data mining models depend on task they accomplish: Association Rules, Clustering, Prediction, and Classification. Neural network is used to find pattern in data. The grouping of neural network model and data mining method can greatly increase the efficiency of data mining methods and it has been broadly used. Different algorithms have been discussed for optimizing the artificial neural network (ANN). ANN combines with other algorithms to find out the high accurate data as compare to traditional algorithm. The role of ANN using data mining techniques is playing an important role in forecasting or prediction about games and weather. This produces high accurate predictions than that of traditional algorithm. Data mining approaches using ANN can also work well. ANN is a highly class algorithm which can be accelerated using neuron. The result of which will produce a high speed up ANN. ANN can also be used for the purpose of extracting rules from trained neural networks.

소셜 미디어 데이터 마이닝을 통한 라이프스타일 호텔 공간 선호 요인에 관한 연구 - 2021년 이후 성수기 중심으로 -

양윤실,김용성,송석재 한국공간디자인학회 2023 한국공간디자인학회논문집 Vol.18 No.1

(Background and Purpose) Instagram, one of the social media platforms, provides image-oriented information and has a greater impact than existing information media by using it directly or leaving it after experience or visit, and the hotel industry is also actively marketing using Instagram. The scope of lifestyle hotels is gradually expanding, but currently, analysis data on architectural spaces for lifestyle hotels in Korea are insufficient. Therefore, this study aims to analyze the characteristics of the lifestyle hotel space targeting millennials with strong personality using the image of a specific platform called Instagram and suggests it as basic data for future lifestyle hotel construction. (Method) To this end, the concept and spatial composition of lifestyle hotels are reviewed through previous studies, and the characteristics thereof are identified. A framework for analysis to analyze spatial components was established, and prior analysis studies using image data from Instagram were conducted. Image data mining was conducted using a neural network model, one of the classification techniques of data mining. Based on this, the space of lifestyle hotels that mainly appear in the image was identified, and spatial preference factors were derived for this. This is to provide basic data on future lifestyle hotel construction plans and present the direction of hotel construction. (Results) Therefore, this study analyzed users' preferred spaces through image mining based on the framework of analysis on the space composition of selected lifestyle hotels, and derived the results that images appeared the most in swimming pools, rooms, lobby lounges, restaurants, bars, elevators, and corridors. After analyzing the preference factors in the main space through image mining in the same space based on the image of the upper space, it was confirmed that the preferred space characteristics of Instagram users are the preference factors for each hotel, such as exhibition elements using colorful patterns or art works, high floor height, round stairs, huge columns, and various color lights. (Conclusions) This analyzed information on users' direct experiences or visits through a large amount of data through a big data analysis method called image data mining for existing hotel architectural spaces. Through data mining of the image shown on Instagram, it was possible to identify the preference factors for the hotel space preferred by users. Therefore, it can be seen that the composition of the space, architecture, interior, and visual elements through exhibition in the space of the lifestyle hotel play a very important role in the hotel space. This study identified the spatial composition of lifestyle hotels and their preference factors as a method of analyzing large amounts of big data through image data mining on Instagram, and it is expected to be used as basic data for lifestyle hotel building plan research. (연구배경 및 목적) 소셜 미디어 플랫폼 중 하나인 인스타그램(Instagram)은 이미지 중심의 정보를 제공하여 직접 사용하거나 체험 또는 방문 후에 남기는 게시물을 통한 정보로 기존 정보 매체보다 큰 영향을 주고 있으며, 호텔 업계에서도 인스타그램을 활용한 마케팅을 적극적으로 펼치고 있다. 라이프스타일 호텔의 범위는 점차 확대되고 있으나, 현재 국내의 라이프스타일 호텔에 대한 건축 공간에 관한 분석 자료는 미비한 실정이다. 이에 본 연구는 개성이 강한 밀레니얼 세대를 타겟으로 한 라이프스타일 호텔 공간을 인스타그램이라는 특정 플랫폼의 이미지를 이용하여 이미지에서 주요하게 나타나는 공간에 대한 특성을 분석하고자 하는 것으로 향후 라이프스타일 호텔 건축에 대한 기초자료로 제안하려고 한다. (연구방법) 이를 위해 선행연구를 통한라이프스타일 호텔의 개념과 공간 구성을 고찰하고 그에 대한 특징을 파악한다. 공간 구성 요소를 분석하기 위한 분석의 틀을설정하고 인스타그램의 이미지 데이터를 활용한 분석 선행 연구를 진행하였다. 데이터 마이닝의 분류 기법 중 하나인 신경망 모델을 활용하여 이미지 데이터 마이닝을 진행하였다. 이를 바탕으로 이미지에서 주로 나타나는 라이프스타일 호텔의 공간을 파악하였으며 그에 대한 공간 선호 요인을 도출하였다. 이는 향후 라이프스타일 호텔 건축 계획에 관한 기초자료로 제공하고자 한다. (결과) 이에 본 연구에서는 선정된 라이프스타일 호텔의 공간 구성에 대한 분석의 틀을 기준으로 이미지 마이닝을 통한 이용자들의 선호 공간을 분석한 결과 수영장과, 객실, 로비 라운지, 레스토랑 ‧ 바, 엘리베이터, 복도 공간에서 이미지가 가장 많이나타났다는 결과를 도출하였다. 이후 상위 공간의 이미지를 기준으로 동일 공간 내 세부 분류 이미지마이닝을 통해 주요 공간에서 나타나는 선호 요인을 분석한 결과 인스타그램 이용자들의 이미지에서 배경이 되는 선호 공간 특성은 화려한 패턴이나 미술작품 등을 활용한 전시 요소, 개방감을 주는 높은 층고, 원형 계단, 거대한 기둥, 다양한 색상 조명 등 호텔별로 가지는 특정한요소가 인스타그램 이미지에서 주로 나타나는 공간 선호 요인임을 확인하였다. (결론) 이는 기존의 호텔 건축 공간에 대해 이미지 데이터 마이닝이라는 빅 데이터 분석 방법을 통해 이용객들의 직접적인 체험이나 방문에 대한 정보를 대량의 데이터를 통해분석하였다. 인스타그램에서 나타난 이미지의 데이터 마이닝을 통해 이용자들의 호텔 공간에 대한 선호 요인을 파악할 수 있었다. 따라서 라이프스타일 호텔의 공간에서 공간의 구성 여부나 건축 및 인테리어, 전시를 통한 시각적 요소는 호텔 공간에서 매우 중요한 역할을 한다는 것을 알 수 있다. 본 연구는 인스타그램의 이미지 데이터 마이닝을 통한 대량의 빅 데이터 분석 방법으로 라이프스타일 호텔의 공간구성과 그에 대한 선호 요인을 파악하였으며 라이프스타일 호텔 건축 계획 연구의 기초자료로 활용되기를 기대한다.