• 스마트미디어저널
• /
• 제9권1호
• /
• pp.45-50
• /
• 2020

딥 러닝의 발전에 따라 추천시스템에서 딥 러닝 기반의 인공신경망을 활용한 연구가 활발히 진행되고 있다. 특히, RNN(Recurrent Neural Network)기반의 추천시스템은 데이터의 순차적 특성을 고려하기 때문에 추천시스템에서 좋은 성과를 보여주고 있다. 본 연구는 RNN기반의 알고리즘인 GRU(Gated Recurrent Unit)와 세션 기반 병렬 미니배치(Session Parallel mini-batch)기법을 활용한 여행경로 추천 시스템을 제안한다. 본 연구는 top1과 bpr(Bayesian personalized ranking) 오차함수의 앙상블을 통해 추천 성과를 향상시켰다. 또한, 데이터 내에 순차적인 특성을 고려한 RNN기반 추천 시스템은 여행경로에 내재된 여행지의 의미가 반영된 추천이 이루어진다는 것을 확인되었다.

• Asia pacific journal of information systems
• /
• 제17권1호
• /
• pp.123-145
• /
• 2007

There are flourishing studies in the acceptance or usage of information systems literature. Most of them have taken the pro - acceptance view. Undesirably, information technologies often provoke users' reactance or resistance. This paper explores one of the negative reactions -psychological reactance. The present paper studies the effects of the users' perception of threatened freedom and personalization degree on intention to use recommendation services. High personalization can be a major motivation for users to accept recommendation systems. However recommendation services are a two-edged sword, which not only provides users the efficiency of decision making but also poses threats to free choice. When people consider that their freedom is reduced or threatened by others, they experience the motivational state to restore the freedom. This motivational state must be considered in understanding usage of information systems, especially personalized services which are designed for persuasion or compliance. This paper empirically investigates the effect of personalization and the psychological reactance on the intention to use information systems in the personalized recommendation context. Users' perception of personalization increases the usefulness of recommendation service while their perception of threat to freedom reduces the intention to use personalized recommendation service. Findings and implications are discussed.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.599-614
• /
• 2021

This paper proposes a digital signage system based on an intelligent recommendation model. The proposed system consists of a server and an edge. The server manages the data, learns the advertisement recommendation model, and uses the trained advertisement recommendation model to determine the advertisements to be promoted in real time. The advertisement recommendation model provides predictions for various products and probabilities. The purchase index between the product and weather data was extracted and reflected using correlation analysis to improve the accuracy of predicting the probability of purchasing a product. First, the user information and product information are input to a deep neural network as a vector through an embedding process. With this information, the product candidate group generation model reduces the product candidates that can be purchased by a certain user. The advertisement recommendation model uses a wide and deep recommendation model to derive the recommendation list by predicting the probability of purchase for the selected products. Finally, the most suitable advertisements are selected using the predicted probability of purchase for all the users within the advertisement range. The proposed system does not communicate with the server. Therefore, it determines the advertisements using a model trained at the edge. It can also be applied to digital signage that requires immediate response from several users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3266-3285
• /
• 2023

With the popularity of online learning, intelligent tutoring systems are starting to become mainstream for assisting online question practice. Surrounded by abundant learning resources, some students struggle to select the proper questions. Personalized question recommendation is crucial for supporting students in choosing the proper questions to improve their learning performance. However, traditional question recommendation methods (i.e., collaborative filtering (CF) and cognitive diagnosis model (CDM)) cannot meet students' needs well. The CDM-based question recommendation ignores students' requirements and similarities, resulting in inaccuracies in the recommendation. Even CF examines student similarities, it disregards their knowledge proficiency and struggles when generating questions of appropriate difficulty. To solve these issues, we first design an enhanced cognitive diagnosis process that integrates students' affection into traditional CDM by employing the non-compensatory bidimensional item response model (NCB-IRM) to enhance the representation of individual personality. Subsequently, we propose an affection-enhanced personalized question recommendation (AE-PQR) method for online learning. It introduces NCB-IRM to CF, considering both individual and common characteristics of students' responses to maintain rationality and accuracy for personalized question recommendation. Experimental results show that our proposed method improves the accuracy of diagnosed student cognition and the appropriateness of recommended questions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.3050-3063
• /
• 2023

Recommendation systems provide personalized products or services to online users by mining their past preferences. Collaborative filtering is a popular recommendation technique because it is easy to implement. However, with the rapid growth of the number of users in recommendation systems, collaborative filtering suffers from serious scalability and sparsity problems. To address these problems, a novel collaborative filtering recommendation algorithm is proposed. The proposed algorithm partitions the users using affinity propagation clustering, and searches for k nearest neighbors in the partition where active user belongs, which can reduce the range of searching and improve real-time performance. When predicting the ratings of active user's unrated items, mean deviation method is used to impute values for neighbors' missing ratings, thus the sparsity can be decreased and the recommendation quality can be ensured. Experiments based on two different datasets show that the proposed algorithm is excellent both in terms of real-time performance and recommendation quality.

• 산업경영시스템학회지
• /
• 제39권4호
• /
• pp.60-66
• /
• 2016

Compound logistics is a service aimed to enhance logistics efficiency by supporting that shippers and consigners jointly use logistics facilities. Many of these services have taken place both domestically and internationally, but the joint logistics services for e-commerce have not been spread yet, since the number of the parcels that the consigners transact business is usually small. As one of meaningful ways to improve utilization of compound logistics, we propose a brokerage service for shipper and consigners based on the hybrid recommendation system using very well-known classification and clustering methods. The existing recommendation system has drawn a relatively low satisfaction as it brought about one-to-one matches between consignors and logistics vendors in that such matching constrains choice range of the users to one-to-one matching each other. However, the implemented hybrid recommendation system based brokerage agent service system can provide multiple choice options to mutual users with descending ranks, which is a result of the recommendation considering transaction preferences of the users. In addition, we applied feature selection methods in order to avoid inducing a meaningless large size recommendation model and reduce a simple model. Finally, we implemented the hybrid recommendation system based brokerage agent service system that shippers and consigners can join, which is the system having capability previously described functions such as feature selection and recommendation. As a result, it turns out that the proposed hybrid recommendation based brokerage service system showed the enhanced efficiency with respect to logistics management, compared to the existing one by reporting two round simulation results.

• 한국의류산업학회지
• /
• 제21권2호
• /
• pp.141-150
• /
• 2019

Online recommendation services help people search for an appropriate product among a huge assortment in stores that also minimize consumers' choice overload. People with a need for uniqueness are likely to prefer this online recommendation service based on individual needs and tastes. This study verifies the effect of consumers' choice overload and similarity avoidance in consumers' evaluation towards an online recommendation service with a focus on innovativeness and use comparability. Two-hundred consumers participated in this study and data were collected through an online survey firm. A mock retailer's webpage was created and showed six types of sneakers, which was presented as a result of product recommendation based on consumers' personal information. Data was analyzed using confirmatory factor analysis (CFA), analysis of variance (ANOVA), and regression analysis. The results show that people with a high similarity avoidance perceive an online recommendation service as an innovative and compatible service. They also perceive a high level of use compatibility for an online recommendation service, especially when it is difficult to choose a product under choice overload. Innovativeness and use compatibility of an online recommendation service increase behavioral intention. The results of this study can contribute to strategies to start online recommendation services from online retailers' websites that identify circumstances in which consumers can adopt innovative services in a positive manner.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3798-3814
• /
• 2022

Social recommendation algorithm can alleviate data sparsity and cold start problems in recommendation system by integrated social information. Among them, matrix-based decomposition algorithms are the most widely used and studied. Such algorithms use dot product operations to calculate the similarity between users and items, which ignores user's potential preferences, reduces algorithms' recommendation accuracy. This deficiency can be avoided by a metric learning-based social recommendation algorithm, which learns the distance between user embedding vectors and item embedding vectors instead of vector dot-product operations. However, previous works provide no theoretical explanation for its plausibility. Moreover, most works focus on the indirect impact of social friends on user's preferences, ignoring the direct impact on user's rating preferences, which is the influence of user rating preferences. To solve these problems, this study proposes a user bias drift social recommendation algorithm based on metric learning (BDML). The main work of this paper is as follows: (1) the process of introducing metric learning in the social recommendation scenario is introduced in the form of equations, and explained the reason why metric learning can replace the click operation; (2) a new user bias is constructed to simultaneously model the impact of social relationships on user's ratings preferences and user's preferences; Experimental results on two datasets show that the BDML algorithm proposed in this study has better recommendation accuracy compared with other comparison algorithms, and will be able to guarantee the recommendation effect in a more sparse dataset.

• 한국멀티미디어학회논문지
• /
• 제21권2호
• /
• pp.242-249
• /
• 2018

In this paper, the customized sports convergence contents curation system is proposed for activation of life sports. The proposed system collects and analyzes profile of social sports group (club, society, etc.) for recommending optimized sports convergence contents to user. In addition, the feedback based on the recommendation result from the user is continuously reflected and the optimal recommendation is made possible. For the system evaluation, the proposed system is tested to 300 users (about 20 sports team) for about 3 months and the system is verified by analyzing the initial recommendation results and recommendation results reflected by user feedback.

• 한국조리학회지
• /
• 제20권5호
• /
• pp.106-110
• /
• 2014

Little is known about the impact of ambience on customers' emotions, satisfaction, and word of mouth recommendation within the context of coffee shops. This study examined the relationships among ambience, emotions, customer satisfaction, and word of mouth recommendation in a coffee shop setting. A total of 303 visitors at 5 coffee shops in a Southwestern state in the U.S. completed questionnaires. Utilizing a structural equation modeling technique, this study demonstrated that ambience significantly influenced emotions and customer satisfaction. In addition, emotions significantly affected customer satisfaction and word of mouth recommendation.