• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.105-114
• /
• 2017

Today, many services are supported on the web sites. Analysis of usage patterns of web site visitors is very important to optimize the use and efficiency of the web sites. In this study, analysis of usage patterns and comparative analysis of user groups were conducted by analyzing web access log provided by BPI Challenge 2016. This data provides access logs to the web site in the IT system of a Dutch Employee Insurance Agency (UWV). The customer information, and the click data describing the customers' behavior when using the agency's web site. In this study, we use process mining techniques to analyze the usage patterns of customers and the characteristics of customer groups, and ultimately improve the service quality of customers using web services.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.215-229
• /
• 2020

The interest in machine learning is growing in all industries, but it is difficult to apply it to real-world tasks because of inexplicability. This paper introduces a case of developing a financial customer churn prediction model for a securities company, and introduces the research results on an attempt to develop a machine learning model that can be explained using the SHAP Value methodology and derivation of interpretability. In this study, a total of six customer churn models are compared and analyzed, and the cause of customer churn is inferred through the classification and data analysis of SHAP Value and the type of customer asset change. Based on the results of this study, it would be possible to use it as a basis for comprehensive judgment, such as using the Value of the deviation prediction result that can infer the cause of the marketing manager's actual customer marketing in the future and establishing a target marketing strategy for each customer.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.568-571
• /
• 2020

최근 빅데이터 기술이 다양한 산업과 접목되고 있다. 그 중 고객 이탈 방지가 최우선인 통신사들 또한 예외가 아닐 수 없다. 이에 본 논문은 통신사 데이터에 머신러닝 알고리즘을 접목. 이탈 예측과 데이터 추이를 분석하고, 이를 시각화 하여 일목요연하게 표출하는 과정을 제공함으로서 통신사의 고객 유치 정책을 위한 토대를 마련할 것이다.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.552-553
• /
• 2024

협력적 필터링은 추천시스템을 구축하는 알고리즘으로 고객별 선호도를 예측하는데 사용되고 있다. 이에 본 연구는 행복감에 영향을 주는 요인인 자존감과 생활여건을 사용하여, 협력적 필터링을 기반으로 한 예측정확도가 높은 모형을 연구하고자 한다. 이를 위해, 자존감과 생활여건에 대한 응답자 간의 유사도 가중치를 각각 계산한 후, 자존감 유사도 가중치를 적용한 모형으로 행복감을 예측하고, 자존감 유사도 가중치에 생활여건 유사도 가중치를 부여한 유사도 가중치를 적용한 모형으로 행복감을 예측하였다. 그 결과 전자의 모형이 후자의 모형보다 예측정확도가 높게 나타났다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.140-141
• /
• 2017

Big data analysis, in the large amount of data stored as the data warehouse which it refers the process of discovering meaningful new correlations, patterns, trends and creating new values. Thus, Big data analysis is an effective analysis of various big data that exist all over the world such as social big data, machine to machine (M2M) sensor data, and corporate customer relationship management data. In the big data era, it has become more important to effectively analyze not only structured data that is well organized in the database, but also unstructured big data such as the internet, social network services, and explosively generated web documents, e-mails, and social data in mobile environments. By the way, a meta analysis refers to a statistical literature synthesis method from the quantitative results of many known empirical studies. We reviewed a total of 750 samples among 50 studies published on the topic related as IDT between 2000 and 2017 in Korea.

• Journal of Digital Convergence
• /
• v.15 no.9
• /
• pp.167-178
• /
• 2017

Big Data is a key asset for the company and a key factor in boosting its competitiveness in the logistics sector. However, there is still a lack of research on how to collect, analyze and utilize Big Data in logistics. In this context, this study has developed a value model applicable to logistics companies based on the results of analysis and application of Big Data in the logistics of previous studies and DHL. The purpose of this study is to improve the operational efficiency and customer experience maximization level of logistics companies through utilization of big data analysis in logistics, to improve competitiveness of big data utilization and to develop new business opportunities. This study has a significance to newly create a value model for utilization of big data analysis in logistics sector and can provide implications for other industries as well as logistics sector in the future.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.593-600
• /
• 2018

Owing to the advancement of Internet and smart devices, access to various media such as social media became easy; thus, a large amount of big data is being produced. Particularly, the companies that provide various Internet services are analyzing the big data by using the MapReduce-based big data analysis techniques to investigate the customer preferences and patterns and strengthen the security. However, with MapReduce, when the big data is analyzed by defining the number of reducer objects generated in the reduce stage as one, the processing rate of big data analysis decreases. Therefore, in this paper, a MapReduce-based split big data analysis method is proposed to improve the log analysis processing rate. The proposed method separates the reducer partitioning stage and the analysis result combining stage and improves the big data processing rate by decreasing the bottleneck phenomenon by generating the number of reducer objects dynamically.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.643-644
• /
• 2014

정보기술의 발달과 인터넷의 확산 등의 사회적인 변화에 따라 고객을 효과적으로 만족시킬 수 있도록 기업은 고객과의 장기적인 관계를 구축하는 고객관계관리(CRM: Customer Relationship Management)을 사용하고 있다. 최근에는 블로그나 SNS등에 기업이 상품이나 서비스를 팔고자 하는 소비자들이 가득 모여 있기 때문에 실시간으로 소비자의 니즈를 파악할 수 있는 방법으로 트위터, 블로그, 카페 등 SNS 상의 빅 데이터를 분석하는 시스템을 이용한다. 본 논문에서는 고객의 보다 효율적인 피드백 수집분석을 위해 기존의 기업/기관에서 운영 및 관리하는 내부 CRM 데이터와 SNS 상의 외부 데이터를 연동하여 분석할 수 있는 이기종 데이터의 통합 분석엔진 시스템을 제안한다. 이를 의료서비스에 적용하여 내부 데이터인 매출, 방문자 수, 진료과 정보, 환자 정보, 고객 불만 유형 등을 분석하고 소셜데이터를 통해 해당 의료기관에 대한 소비자 경험 (진료, 시설 등) 정보를 수집한다.

• Journal of Digital Convergence
• /
• v.14 no.9
• /
• pp.317-323
• /
• 2016

Big Data is now seen as a major asset in the company's competitiveness, its influence in the future is expected to grow. Companies that recognize the importance are already actively engaged with Big Data in product development and marketing, which are increasingly applied across sectors of society, including politics, sports. However, lack of knowledge of the system implementation and high costs are still a big obstacles to the introduction of Big Data and systems. It is an objective in this study to build a Big Data system, which is based on open source Hadoop and Hive among Big Data systems, utilizing POS sales data of small and medium-sized offline markets. This approach of convergence is expected to improve existing sales systems that have been simply focusing on profit and loss analysis. It will also be able to use it as the basis for the decisions of the executive to enable prediction of the consumption patterns of customer preference and demand in advance.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.353-354
• /
• 2021

본 연구에서는 빠르게 발전하는 남성 화장품 시장 트렌드에 맞춰서 남성 고객과 남성 화장품을 타겟으로 하는 기업에 유용한 정보를 제공할 수 있는 데이터베이스 시스템을 구축하고자 한다. 아직까지는 여성에 비해 남성 고객과 남성 화장품에 대한 데이터 분석 및 연구가 현저히 적은 편이다. 본 연구는 남성 고객의 데이터와 빅데이터 자료를 바탕으로 구매율이 높은 상위 10개 제품명과 브랜드명, 소비자가 원하는 가격대의 유명하고 인기있는 제품, 특정 피부고민을 가진 고객이 구매한 제품 중 알레르기 유발 물질이 포함된 제품의 정보와 같은 유용한 정보들을 데이터베이스 시스템을 활용하여 산출해냈다. 이를 통해, 남성 화장품 시장이 앞으로 나아갈 방향에 대해 파악하고 국내 남성 화장품 시장의 발전에도 이바지할 수 있을 것으로 예측된다.