• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.369-384
• /
• 2021

In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracy of model recommendation will be greatly affected. To solve this problem, a personalized product recommendation method using deep factorization machine (DeepFM) to analyze user behavior is proposed. Firstly, the K-means clustering algorithm is used to cluster the original log data from the perspective of similarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationship between low- and high-order feature combinations is learned from log data, and the click rate prediction model is constructed. Finally, based on the predicted click-through rate, products are recommended to users in sequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and 0.0253, respectively, on the Criteo dataset, and 0.7836 and 0.0348 on the KDD2012 Cup dataset, respectively. Compared with other newer recommendation methods, the proposed method can achieve better recommendation effect.

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.1-7
• /
• 2020

As the demand for health screening increases, there is a need for efficient design of screening items. We build machine learning models for health screening and recommend screening items to provide personalized health care service. When offline, a synthetic data set is generated based on guidelines and clinical results from institutions, and a machine learning model for each screening item is generated. When online, the recommendation server provides a recommendation list of screening items in real time using the customer's health condition and machine learning models. As a result of the performance analysis, the accuracy of the learning model was close to 100%, and server response time was less than 1 second to serve 1,000 users simultaneously. This paper provides an adaptive and automatic recommendation in response to changes in the new screening environment.

• 센서학회지
• /
• 제24권1호
• /
• pp.62-68
• /
• 2015

The MPEG user description (MPEG-UD) which is a standard under exploration to ensure interoperability among customized recommendation services has been contributed since MPEG $104^{th}$ meeting at 2013. Twenty-two use cases that were divided into different applications have been proposed in the MEPG meetings. Most of use cases were referred to specific and restricted regarding to applications, it appears to miss an overall and explicit infra-structure. In this paper we describe a reference model, namely methodology to overcome aforementioned problems. Thereafter, we have applied reference model to context-based recommendation system to demonstrate the methodology and MPEG-UD schemas. In addition, we propose a development process of recommendation system in compliance with MPEG-UD.

• 디지털융복합연구
• /
• 제17권6호
• /
• pp.113-121
• /
• 2019

본 연구는 수직적으로 확장된 기술수용모델(TAM)을 토대로 사용자반응에 영향을 미치는 주요한 신념변수인 지각된 유용성과 지각된 사용용이성에 지각된 유희성을 추가하고, 키오스크 서비스의 만족과 추천의도에 영향을 미치는 신념변수의 영향력을 실증적으로 검증해보고자 하였다. 그 결과, 첫째, 키오스크의 유용성과 사용편리성을 지각하면 만족하는 것으로 나타났다. 둘째, 키오스크의 지각된 유용성과 지각된 유희성은 키오스크 서비스의 추천의도에 유의한 정(+)의 영향을 미치는 것으로 나타났다. 셋째, 키오스크 서비스에 만족한 사용자는 강한 추천의도를 가지는 것으로 나타났다. 이와 같은 연구결과는 기존 기술수용모델에서 규명한 새로운 정보기술의 유용성과 사용편리성이 사용자반응(만족과 추천의도)에 영향을 미치는 주요한 변수임을 재입증 해주고 있으며, 새롭게 추가한 지각된 유희성이 키오스크 서비스의 만족을 매개하지 않고도 추천의도를 활성화시킬 수 있다는 것을 의미한다. 본 연구의 결과는 키오스크 서비스의 지각된 유희성이 추가된 확장된 신념변수와 추천의도 간의 관계를 연구모형에 도입하고 실증적으로 검증했다는 점에서 의의가 있다고 판단된다.

• 한국멀티미디어학회논문지
• /
• 제25권9호
• /
• pp.1367-1374
• /
• 2022

In this paper, we propose an automatic cosmetic foundation recommendation system that suggests a good foundation product based on the user's skin color. The proposed system receives and preprocesses user images and detects skin color with OpenCV and machine learning algorithms. The system then compares the performance of the training model using XGBoost, Gradient Boost, Random Forest, and Adaptive Boost (AdaBoost), based on 550 datasets collected as essential bestsellers in the United States. Based on the comparison results, this paper implements a recommendation system using the highest performing machine learning model. As a result of the experiment, our system can effectively recommend a suitable skin color foundation. Thus, our system model is 98% accurate. Furthermore, our system can reduce the selection trials of foundations against the user's skin color. It can also save time in selecting foundations.

• Journal of Information Technology Applications and Management
• /
• 제27권6호
• /
• pp.141-151
• /
• 2020

The job mismatch between job seekers and SMEs is becoming more and more intensifying with the serious difficulties in youth employment. In this study, a bi-directional content-based metric learning model is proposed to recommend suitable jobs for job seekers and suitable job seekers for SMEs, respectively. The proposed model not only enables bi-directional recommendation, but also enables HR matching without relearning for new job seekers and new job offers. As a result of the experiment, the proposed model showed superior performance in terms of precision, recall, and f1 than the existing collaborative filtering model named NCF+GMF. The proposed model is also confirmed that it is an evolutionary model that improves performance as training data increases.

• 한국콘텐츠학회논문지
• /
• 제11권2호
• /
• pp.22-30
• /
• 2011

품질뿐만 아니라 물질적 풍요가 되어가는 IT융합 환경에서 상황정보를 파악하는 것은 개인화 추천 서비스 전략의 중요한 성공요소가 되고 있다. 본 논문에서는 서비스 온톨로지 기반의 상황인식 모델링을 이용한 추천을 제안하였다. 이기종 디바이스 구축을 위해 OSGi 프레임워크 기반의 데이터 획득 모듈을 구축하고 온톨로지 기반의 상황정보 모델을 개발한다. 상황정보 모델을 위해서 추천 시스템에 필요한 상황정보를 추출하고 분류한다. 상황정보를 사용하여 온톨로지 기반의 상황인식 모델을 개발하고 협력적 필터링의 추천에 반영한다. 상황인식 모델은 Na$\"{\i}$ve Bayes 분류자를 사용하여 상황에 따라 서비스를 선택한 정보를 반영하고 사용자에게 제공한다. 제안한 방법의 성능 평가를 하기 위해 대응표본 T-검정을 실시하여 유용성을 검증하였다. 평가 결과, 서비스에 대한 만족도의 차이가 통계적으로 의미가 있음을 증명하였고 높은 만족도를 보임을 확인하였다.

• 한국컴퓨터정보학회논문지
• /
• 제28권12호
• /
• pp.57-66
• /
• 2023

본 연구에서는 딥러닝 기법과 정서적 AI를 적용하여 사용자의 감정 상태를 추정하고 이를 추천 과정에 반영할 수 있는 추천 시스템에 대한 새로운 연구 프레임워크를 제안한다. 이를 위해 분노, 혐오, 공포, 행복, 슬픔, 놀람, 중립의 7가지 감정을 각각 분류하는 감정분류모델을 구축하고, 이 결과를 추천 과정에 반영할 수 있는 모형을 제안한다. 그러나 일반적인 감정 분류 데이터에서는 각 레이블 간 분포 비율의 차이가 크기 때문에 일반화된 분류 결과를 기대하기 어려울 수 있다. 본 연구에서는 감정 이미지 데이터에서 혐오감 등의 감정 개수가 부족한 경우가 많으므로 데이터 증강을 이용한다. 마지막으로, 이미지 증강을 통해 데이터 기반의 감정 예측 모델을 추천시스템에 반영하는 방법을 제안한다.

• Asia pacific journal of information systems
• /
• 제16권4호
• /
• pp.239-254
• /
• 2006

Location-based advertising or application has been one of the drivers of third-generation mobile operators' marketing efforts in the past few years. As a result, many studies on location-based marketing or advertising have been proposed for recent several years. However, these approaches have two common shortcomings. First. most of them just suggested the theoretical architectures, which were too abstract to apply it to the real-world cases. Second, many of these approaches only consider service provider (seller) rather than customers (buyers). Thus, the prior approaches fit to the automated sales or advertising rather than the implementation of CRM. To mitigate these limitations, this study presents a novel advertisement recommendation model for mobile users. We call our model MAR-CF (Mobile Advertisement Recommender using Collaborative Filtering). Our proposed model is based on traditional CF algorithm, but we adopt the multi-dimensional personalization model to conventional CF for enabling location-based advertising for mobile users. Thus, MAR-CF is designed to make recommendation results for mobile users by considering location, time, and needs type. To validate the usefulness of our recommendation model. we collect the real-world data for mobile advertisements, and perform an empirical validation. Experimental results show that MAR-CF generates more accurate prediction results than other comparative models.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권2호
• /
• pp.91-95
• /
• 2007

Main goal of web recommendation system is to study how user behavior on a website can be predicted by analyzing web log data which contain the visited web pages. Many researches of the web recommendation system have been studied. To construct web recommendation system, web mining is needed. Especially, web usage analysis of web mining is a tool for recommendation model. In this paper, we propose web recommendation system using grid based support vector machines for improvement of web recommendation system. To verify the performance of our system, we make experiments using the data set from our web server.