• Management & Information Systems Review
• /
• v.35 no.3
• /
• pp.57-79
• /
• 2016

It is required to derive various conclusions by identifying the type of power and the relationship between SCMs and presenting practical implications. Thus, we can identify the differential effects of each type of power on SCM performance. We can contribute to develop the practical implications at more sophisticated multi-dimension by comparing results of this study with various SCM theories. Through previous studies, the source of power is largely divided into binding power and non-binding power. Binding power is classified into behavior coercion, binding reward and relationship legitimacy. Non-binding power is classified into work expertise, information superiority and value compliance. Enterprises should fully understand and recognize partners within supply chains including understanding of the source of power, imbalance and results. Thus, we look into types of power and effects on trust and commitment, and identify a causal relationship leading to collaboration and SCM performance. Specific research results are as follows. First, the binding power did not give a significant effect to the trust. However, the binding power gave a positively(+) significant effect to the commitment. Second, non-binding power showed a significant effect on both trust and commitment. As a result of analysis on total effects, it was shown that non-binding power gave indirect effects to collaboration and SCM performance. Third, it was shown that both trust and commitment significantly affected collaboration. From the perspectives of social exchange theory and trading cost theory among inter-organizational relationship theory, it may lead to SCM performance of trust, commitment and collaboration. Moreover, it was found that association of each attribute of power led to the significant result. Fourth, it was shown that trust and collaboration significantly affected SCM performance. However, commitment did not directly affect SCM performance, but it indirectly significantly affected SCM performance through collaboration. Proper use of this power can firmly build partnerships between members of the supply chain and induce the improvement on supply chain performance and satisfaction of members.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.265-274
• /
• 2021

In this paper, we propose a novel recommendation model based on Doc2vec using search keywords and product details. Until now, a lot of prior studies on recommender systems have proposed collaborative filtering (CF) as the main algorithm for recommendation, which uses only structured input data such as customers' purchase history or ratings. However, the use of unstructured data like online customer review in CF may lead to better recommendation. Under this background, we propose to use search keyword data and product detail information, which are seldom used in previous studies, for product recommendation. The proposed model makes recommendation by using CF which simultaneously considers ratings, search keywords and detailed information of the products purchased by customers. To extract quantitative patterns from these unstructured data, Doc2vec is applied. As a result of the experiment, the proposed model was found to outperform the conventional recommendation model. In addition, it was confirmed that search keywords and product details had a significant effect on recommendation. This study has academic significance in that it tries to apply the customers' online behavior information to the recommendation system and that it mitigates the cold start problem, which is one of the critical limitations of CF.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.781-784
• /
• 2019

최근 AI를 산업 서비스에 적용하기 위해 많은 회사들이 활발히 연구를 하고 있다. 아마존과 넷플릭스 같은 거대 기업들은 이미 빅데이터와 AI 머신러닝을 이용한 추천 시스템을 구현하였고 아마존은 매출의 35%가 추천에 의해 발생하고 넷플릭스 75%의 사용자가 추천을 통해 영화를 선택한다고 보고되었다. 이러한 두 기업의 높은 추천 효율성의 이유는 협업 필터링(Collaborative filtering)과 같은 다양한 추천 알고리즘과 방대한 상품 및 고객 행동(구매, 시청 등) 데이터 등이 존재하고 있기 때문이다. 기계학습에서 알고리즘 학습을 위한 데이터의 양이 많지 않을 경우 알고리즘의 성능을 보장할 수 없다는 것이 일반적인 의견이다. 방대한 데이터를 가진 기업에서 추천 알고리즘을 적극적으로 활용 및 연구하고 있는 것도 이러한 이유 때문이다. 반면, 오프라인 및 여행사 기반에서 온라인 기반으로 영역을 차츰 확대하고 있는 항공 서비스 고객 데이터의 경우, 산업의 특성상 많은 회원에 비해 고객 1명당 온라인에서 활동하는 이력이 많지 않은 것이 특징이다. 이는, 추천 알고리즘을 통한 서비스 제공에서 큰 제약사항으로 작용한다. 본 연구에서는, 이러한 희박한 고객 활동 데이터에서 최신성 기반의 추천 시스템을 통하여 제약사항을 극복하고 추천 효율을 높이는 방법을 제안한다. 고객의 최근 접속 이력 로그를 시간 기준으로 데이터 셋을 분할하여 추천 알고리즘에 반영하였을 때, 추천된 노선에 대한 고객의 반응을 추천 성능 지표인 CTR(Click-Through Rate)로 측정하여 성능을 확인해 보았다.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.4
• /
• pp.797-808
• /
• 2012

In smart work environment, a company provides employees a flexible work environment for tele-working using mobile phone or portable devices. On the other hand, such environment are exposed to the risks which the attacker can intrude into computer systems or leak personal information of smart-workers' and gain a company's sensitive information. To reduce these risks, the security administrator needs to analyze the usage patterns of employees and detect abnormal behaviors by monitoring VPN(Virtual Private Network) access log. This paper proposes a decision support system that can notify the status by using visualization and similarity measure through clustering analysis. On average, 88.7% of abnormal event can be detected by this proposed method. With this proposed system, the security administrator can detect abnormal behaviors of the employees and prevent account theft.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.311-328
• /
• 2022

Because of the spread of smartphones due to the development of information and communication technology, online shopping mall services can be used on computers and mobile devices. As a result, the number of users using the online shopping mall service increases rapidly, and the types of products traded are also growing. Therefore, to maximize profits, companies need to provide information that may interest users. To this end, the recommendation system presents necessary information or products to the user based on the user's past behavioral data or behavioral purchase records. Representative overseas companies that currently provide recommendation services include Netflix, Amazon, and YouTube. These companies support users' purchase decisions by recommending products to users using ratings, purchase records, and clickstream data that users give to the items. In addition, users refer to the ratings left by other users about the product before buying a product. Most users tend to provide ratings only to products they are satisfied with, and the higher the rating, the higher the purchase intention. And recently, e-commerce sites have provided users with the ability to vote on whether product reviews are helpful. Through this, the user makes a purchase decision by referring to reviews and ratings of products judged to be beneficial. Therefore, in this study, the correlation between the product rating and the helpful information of the review is identified. The valuable data of the evaluation is reflected in the recommendation system to check the recommendation performance. In addition, we want to compare the results of skipping all the ratings in the traditional collaborative filtering technique with the recommended performance results that reflect only the 4 and 5 ratings. For this purpose, electronic product data collected from Amazon was used in this study, and the experimental results confirmed a correlation between ratings and review usefulness information. In addition, as a result of comparing the recommendation performance by reflecting all the ratings and only the 4 and 5 points in the recommendation system, the recommendation performance of remembering only the 4 and 5 points in the recommendation system was higher. In addition, as a result of reflecting review usefulness information in the recommendation system, it was confirmed that the more valuable the review, the higher the recommendation performance. Therefore, these experimental results are expected to improve the performance of personalized recommendation services in the future and provide implications for e-commerce sites.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.145-165
• /
• 2023

Recommendation system plays a significant role on relieving difficulties of selecting information among rapidly increasing amount of information caused by the development of the Internet and on efficiently displaying information that fits individual personal interest. In particular, without the help of recommendation system, E-commerce and OTT companies cannot overcome the long-tail phenomenon, a phenomenon in which only popular products are consumed, as the number of products and contents are rapidly increasing. Therefore, the research on recommendation systems is being actively conducted to overcome the phenomenon and to provide information or contents that are aligned with users' individual interests, in order to induce customers to consume various products or contents. Usually, collaborative filtering which utilizes users' historical behavioral data shows better performance than contents-based filtering which utilizes users' preferred contents. However, collaborative filtering can suffer from cold-start problem which occurs when there is lack of users' historical behavioral data. In this paper, hybrid music recommendation system, which can solve cold-start problem, is proposed based on the playlist data of Melon music streaming service that is given by Kakao Arena for music playlist continuation competition. The goal of this research is to use music tracks, that are included in the playlists, and metadata of music tracks and playlists in order to predict other music tracks when the half or whole of the tracks are masked. Therefore, two different recommendation procedures were conducted depending on the two different situations. When music tracks are included in the playlist, LightFM is used in order to utilize the music track list of the playlists and metadata of each music tracks. Then, the result of Item2Vec model, which uses vector embeddings of music tracks, tags and titles for recommendation, is combined with the result of LightFM model to create final recommendation list. When there are no music tracks available in the playlists but only playlists' tags and titles are available, recommendation was made by finding similar playlists based on playlists vectors which was made by the aggregation of FastText pre-trained embedding vectors of tags and titles of each playlists. As a result, not only cold-start problem can be resolved, but also achieved better performance than ALS, BPR and Item2Vec by using the metadata of both music tracks and playlists. In addition, it was found that the LightFM model, which uses only artist information as an item feature, shows the best performance compared to other LightFM models which use other item features of music tracks.

• Information Systems Review
• /
• v.17 no.3
• /
• pp.95-111
• /
• 2015

The recommendation system automatically provides the predicted items which are expected to be purchased by analyzing the previous customer behaviors. This recommendation system has been applied to many e-commerce businesses, and it is generating positive effects on user convenience as well as the company's revenue. However, there are several limitations of the existing recommendation systems. They do not reflect specific criteria for evaluating products or the factors that affect customer buying decisions. Thus, our research proposes a collaborative recommendation model algorithm that utilizes each customer's online product reviews. This study deploys topic modeling method for customer opinion mining. Also, it adopts a kernel-based machine learning concept by selecting kernels explaining individual similarities in accordance with customers' purchase history and online reviews. Our study further applies a multiple kernel learning algorithm to integrate the kernelsinto a combined model for predicting the product ratings, and it verifies its validity with a data set (including purchased item, product rating, and online review) of BestBuy, an online consumer electronics store. This study theoretically implicates by suggesting a new method for the online recommendation system, i.e., a collaborative recommendation method using topic modeling and kernel-based learning.