• Management & Information Systems Review
• /
• v.35 no.3
• /
• pp.115-130
• /
• 2016

This study aims to identify which social information have significant influence on the improvement of recommendation trust and how these effects can be different according to the product involvement level. Based on the relevant literature reviews, this study posits four characteristics of recommendation trust, which are closeness, similarity, sincerity, and reputation, and established a research model for the relationship between social information and recommendation trust. And we found a moderating effect of product involvement on the relationship between social information and recommendation trust. 205 trust relationships(links) from 55 respondents of Google Docs. survey data have been collected and tested using multiple regression and hierarchical regression analysis. The results of our hypotheses testing are summarized as follows. Firstly, four social information characteristics of closeness, similarity, sincerity, and reputation have a significantly positive effect on recommendation trust. Secondly, a moderating effect of product involvement between recommendation trust and antecedents (e.g., closeness and reputation) of social information is significant. From the results, we provide theoretical and managerial implications, and suggestions for further research.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.29 no.2
• /
• pp.59-75
• /
• 2004

Recommendation is a personalized information filtering technology to help customers find which products they would like to purchase. Collaborative filtering works by matching customer preferences to other customers in making recommendations. But collaborative filtering based recommendations have two major limitations, sparsity and scalability. To overcome these problems we suggest using adjusted product hierarchy, grain. This methodology focuses on dimensionality reduction and uses a marketer's specific knowledge or experience to improve recommendation quality. The qualify of recommendations using each grain is compared with others by several experimentations. Experiments present that the usage of a grain holds the promise of allowing CF-based recommendations to scale to large data sets and at the same time produces better recommendations. In addition. our methodology is proved to save the computation time by 3∼4 times compared with collaborative filtering.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.914-915
• /
• 2017

Importance and usage of the recommender system increases with the increase of information. The accuracy of the system recommendation primarily depends on the data. There is a problem in recommender systems, known as cold start problem. The lack of data about new products and users causes the cold start problem, and the system will not be able to give correct recommendation. This paper deals with cold start problem by comparing product specification and the review of the resembled products. The user, who likes the resembled product of the new one has more probability of taking interest in the new product as well. However, if a user disagreed with resembled product due to some reasons which the user mentioned in the reviews. The new product overcomes that issue, so the user will greatly accept the new product. Therefore, the system needs to recommend new product to those users as well, in this way the cold start problem will get resolved.

• Fashion & Textile Research Journal
• /
• v.17 no.2
• /
• pp.216-226
• /
• 2015

This study identifies factors of perceived risk of up-cycling fashion products and investigates perceived risk factors that influence consumers' trust, purchase intention, and recommendation intention towards upcycling fashion products. We also examine the relationship of trust, purchase intention, and recommendation intention for upcycling fashion products. A qualitative research method using a free narrative form and depth interview were used. The perceived risk from up-cycling fashion products generated 5 factor solutions: aesthetic risk, sanitary risk, social risk, performance risk, and economic risk. Next, 201 effective data were collected from a questionnaire survey and analyzed with SPSS 22.0. The results are summarized as follows. First, aesthetic risk and performance risk had a negative effect on products. Second, aesthetic risk and performance risk had negative influence on purchase intention for upcycling fashion products. Third, performance risk had a negative impact on recommendation intention for upcycling fashion products. Fourth, trust had positive effect on purchase intention and recommendation intention for upcycling fashion products. The results of the current study provides various theoretical and practical implications for marketers and retailers interested in up-cycling fashion products.

• Journal of Intelligence and Information Systems
• /
• v.7 no.2
• /
• pp.153-177
• /
• 2001

Nowadays, product recommendation is one of the important issues regarding both CRM and Internet shopping mall. Generally, a recommendation system tracks past actions of a group of users to make a recommendation to individual members of the group. The computer-mediated marketing and commerce have grown rapidly and thereby automatic recommendation methodologies have got great attentions. But the researches and commercial tools for product recommendation so far, still have many aspects that merit further considerations. To supplement those aspects, we devise a recommendation methodology by which we can get further recommendation effectiveness when applied to Internet shopping mall. The suggested methodology is based on web log information, product taxonomy, association rule mining, and decision tree learning. To implement this we also design and intelligent Internet shopping mall support system based on agent technology and develop it as a prototype system. We applied this methodology and the prototype system to a leading Korean Internet shopping mall and provide some experimental results. Through the experiment, we found that the suggested methodology can perform recommendation tasks both effectively and efficiently in real world problems. Its systematic validity issues are also discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• 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.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.42 no.5
• /
• pp.871-883
• /
• 2018

This study tests consumer responses to online product recommendation service offered by a website. A product recommendation service refers to a filtering system that predicts and shows items that consumers would like to purchase based on their searches or pre-purchase information. The survey is conducted on 300 people in an age group between 20 and 40 years in a panel of an online survey firm. Data are analyzed using confirmatory factor analysis and structural equation modeling by AMOS 20.0. The results show that personalization quality does not have a significant effect on trust, but relationship quality and technology quality have a positive effect on trust. Three types of quality of recommendation service also have a positive effect on commitment. Trust and commitment are factors that increase service usage intentions. In addition, this study reveals the moderating effect of light users vs heavy users based on online shopping time. Light users show a negative effect of personalization quality on trust, indicating that they are likely to be uncomfortable to the service using personal information, compared to heavy users. This study also finds that trust vs commitment is an important factor increasing service usage intentions for heavy users vs light users.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.279-286
• /
• 2006

One of the widely used methods for product recommendation in Internet storefronts is matching product features against target customer profiles. When using this method, it's very important to choose a suitable subset of features for recommendation efficiency and performance, which, however, has not been rigorously researched so far. In this paper, we utilize a dataset collected from a virtual shopping experiment in a Korean Internet book shopping mall to compare several popular methods from other disciplines for selecting features for product recommendation: the vector-space model, TFIDF(Term Frequency-Inverse Document Frequency), the mutual information method, and the singular value decomposition(SVD). The application of SVD showed the best performance in the analysis results.

• Journal of Intelligence and Information Systems
• /
• v.13 no.1
• /
• pp.91-105
• /
• 2007

This research suggests a recommendation system that enables bidirectional communications between the user and system using a utility range-based product recommendation algorithm in order to provide more dynamic and personalized recommendations. The main idea of the proposed algorithm is to find the utility ranges of products based on user specified preference information and calculate the similarity by using overlapping probability of two range values. Based on the probability, we determine what products are similar to each other among the products in the product list of collaborative companies. We have also developed a Web-based application system to recommend similar products to the customer. Using the system, we carry out the experiments for the performance evaluation of the procedure. The experimental study shows that the utility range-based approach is a viable solution to the similar product recommendation problems from the viewpoint of both accuracy and satisfaction rate.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.69-86
• /
• 2021

As artificial intelligence technology advances, personalized recommendation systems using big data have attracted huge attention. In the case of beauty products, product preferences are clearly divided depending on customers' skin types and sensitivity along with individual tastes, so it is necessary to provide customized recommendation services based on accumulated customer data. Therefore, by employing deep learning methods, this study proposes a neural network-based recommendation model utilizing both product search history and context information such as gender, skin types and skin worries of customers. The results show that our model with context information outperforms collaborative filtering-based recommender system models using customer search history.