• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.93-110
• /
• 2015

The recommender system is a system which recommends products to the customers who are likely to be interested in. Based on automated information filtering technology, various recommender systems have been developed. Collaborative filtering (CF), one of the most successful recommendation algorithms, has been applied in a number of different domains such as recommending Web pages, books, movies, music and products. But, it has been known that CF has a critical shortcoming. CF finds neighbors whose preferences are like those of the target customer and recommends products those customers have most liked. Thus, CF works properly only when there's a sufficient number of ratings on common product from customers. When there's a shortage of customer ratings, CF makes the formation of a neighborhood inaccurate, thereby resulting in poor recommendations. To improve the performance of CF based recommender systems, most of the related studies have been focused on the development of novel algorithms under the assumption of using a single profile, which is created from user's rating information for items, purchase transactions, or Web access logs. With the advent of big data, companies got to collect more data and to use a variety of information with big size. So, many companies recognize it very importantly to utilize big data because it makes companies to improve their competitiveness and to create new value. In particular, on the rise is the issue of utilizing personal big data in the recommender system. It is why personal big data facilitate more accurate identification of the preferences or behaviors of users. The proposed recommendation methodology is as follows: First, multimodal user profiles are created from personal big data in order to grasp the preferences and behavior of users from various viewpoints. We derive five user profiles based on the personal information such as rating, site preference, demographic, Internet usage, and topic in text. Next, the similarity between users is calculated based on the profiles and then neighbors of users are found from the results. One of three ensemble approaches is applied to calculate the similarity. Each ensemble approach uses the similarity of combined profile, the average similarity of each profile, and the weighted average similarity of each profile, respectively. Finally, the products that people among the neighborhood prefer most to are recommended to the target users. For the experiments, we used the demographic data and a very large volume of Web log transaction for 5,000 panel users of a company that is specialized to analyzing ranks of Web sites. R and SAS E-miner was used to implement the proposed recommender system and to conduct the topic analysis using the keyword search, respectively. To evaluate the recommendation performance, we used 60% of data for training and 40% of data for test. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. A widely used combination metric called F1 metric that gives equal weight to both recall and precision was employed for our evaluation. As the results of evaluation, the proposed methodology achieved the significant improvement over the single profile based CF algorithm. In particular, the ensemble approach using weighted average similarity shows the highest performance. That is, the rate of improvement in F1 is 16.9 percent for the ensemble approach using weighted average similarity and 8.1 percent for the ensemble approach using average similarity of each profile. From these results, we conclude that the multimodal profile ensemble approach is a viable solution to the problems encountered when there's a shortage of customer ratings. This study has significance in suggesting what kind of information could we use to create profile in the environment of big data and how could we combine and utilize them effectively. However, our methodology should be further studied to consider for its real-world application. We need to compare the differences in recommendation accuracy by applying the proposed method to different recommendation algorithms and then to identify which combination of them would show the best performance.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.305-316
• /
• 2011

Recommender system is the system which, by using automated information filtering technology, recommends products or services to the customers who are likely to be interested in. Those systems are widely used in many different Web retailers such as Amazon.com, Netfix.com, and CDNow.com. Various recommender systems have been developed. Among them, Collaborative Filtering (CF) has been known as the most successful and commonly used approach. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. However, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting in advance whether the performance of CF recommender system is acceptable or not is practically important and needed. In this study, we propose a decision making guideline which helps decide whether CF is adoptable for a given application with certain transaction data characteristics. Several previous studies reported that sparsity, gray sheep, cold-start, coverage, and serendipity could affect the performance of CF, but the theoretical and empirical justification of such factors is lacking. Recently there are many studies paying attention to Social Network Analysis (SNA) as a method to analyze social relationships among people. SNA is a method to measure and visualize the linkage structure and status focusing on interaction among objects within communication group. CF analyzes the similarity among previous ratings or purchases of each customer, finds the relationships among the customers who have similarities, and then uses the relationships for recommendations. Thus CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. Under the assumption that SNA could facilitate an exploration of the topological properties of the network structure that are implicit in transaction data for CF recommendations, we focus on density, clustering coefficient, and centralization which are ones of the most commonly used measures to capture topological properties of the social network structure. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. We explore how these SNA measures affect the performance of CF performance and how they interact to each other. Our experiments used sales transaction data from H department store, one of the well?known department stores in Korea. Total 396 data set were sampled to construct various types of social networks. The dependant variable measuring process consists of three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used UCINET 6.0 for SNA. The experiments conducted the 3-way ANOVA which employs three SNA measures as dependant variables, and the recommendation accuracy measured by F1-measure as an independent variable. The experiments report that 1) each of three SNA measures affects the recommendation accuracy, 2) the density's effect to the performance overrides those of clustering coefficient and centralization (i.e., CF adoption is not a good decision if the density is low), and 3) however though the density is low, the performance of CF is comparatively good when the clustering coefficient is low. We expect that these experiment results help firms decide whether CF recommender system is adoptable for their business domain with certain transaction data characteristics.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1B
• /
• pp.73-85
• /
• 2004

SIn this paper, we introduce our experience for designing and implementing new concept of a global XML-based Peer-to-Peer (P2P) engine to support various P2P applications, and interconnection among PC, Web and mobile computing environments. The proposed P2P engine can support to heterogeneous data exchanges and web interconnection by facilitating with the text-base XML while message exchange are necessary. It is also to provide multi-level security functions as well as to apply different types of security algorithms. The system consist of four modules; a message dispatcher to scheduling and filtering the message, a SecureNet to providing security services and data transmission, a Discovery Manager to constructing peer-to-peer networking, and a Repository Manager to processing data management including XML documents. As a feasibility test, we implement various P2P services such as chatting as a communication service, white-board as an authoring tool set during collaborative working, and a file system as a file sharing service. We also compared the proposed system to a Gnutella in order to measure performance of the systems.

• Asia pacific journal of information systems
• /
• v.20 no.1
• /
• pp.81-99
• /
• 2010

Lately, in consumers' markets the number of new items is rapidly increasing at an overwhelming rate while consumers have limited access to information about those new products in making a sensible, well-informed purchase. Therefore, item providers and customers need a system which recommends right items to right customers. Also, whenever new items are released, for instance, the recommender system specializing in new items can help item providers locate and identify potential customers. Currently, new items are being added to an existing system without being specially noted to consumers, making it difficult for consumers to identify and evaluate new products introduced in the markets. Most of previous approaches for recommender systems have to rely on the usage history of customers. For new items, this content-based (CB) approach is simply not available for the system to recommend those new items to potential consumers. Although collaborative filtering (CF) approach is not directly applicable to solve the new item problem, it would be a good idea to use the basic principle of CF which identifies similar customers, i,e. neighbors, and recommend items to those customers who have liked the similar items in the past. This research aims to suggest a hybrid recommendation procedure based on the preference boundary of target customer. We suggest the hybrid recommendation procedure using the preference boundary in the feature space for recommending new items only. The basic principle is that if a new item belongs within the preference boundary of a target customer, then it is evaluated to be preferred by the customer. Customers' preferences and characteristics of items including new items are represented in a feature space, and the scope or boundary of the target customer's preference is extended to those of neighbors'. The new item recommendation procedure consists of three steps. The first step is analyzing the profile of items, which are represented as k-dimensional feature values. The second step is to determine the representative point of the target customer's preference boundary, the centroid, based on a personal information set. To determine the centroid of preference boundary of a target customer, three algorithms are developed in this research: one is using the centroid of a target customer only (TC), the other is using centroid of a (dummy) big target customer that is composed of a target customer and his/her neighbors (BC), and another is using centroids of a target customer and his/her neighbors (NC). The third step is to determine the range of the preference boundary, the radius. The suggested algorithm Is using the average distance (AD) between the centroid and all purchased items. We test whether the CF-based approach to determine the centroid of the preference boundary improves the recommendation quality or not. For this purpose, we develop two hybrid algorithms, BC and NC, which use neighbors when deciding centroid of the preference boundary. To test the validity of hybrid algorithms, BC and NC, we developed CB-algorithm, TC, which uses target customers only. We measured effectiveness scores of suggested algorithms and compared them through a series of experiments with a set of real mobile image transaction data. We spilt the period between 1st June 2004 and 31st July and the period between 1st August and 31st August 2004 as a training set and a test set, respectively. The training set Is used to make the preference boundary, and the test set is used to evaluate the performance of the suggested hybrid recommendation procedure. The main aim of this research Is to compare the hybrid recommendation algorithm with the CB algorithm. To evaluate the performance of each algorithm, we compare the purchased new item list in test period with the recommended item list which is recommended by suggested algorithms. So we employ the evaluation metric to hit the ratio for evaluating our algorithms. The hit ratio is defined as the ratio of the hit set size to the recommended set size. The hit set size means the number of success of recommendations in our experiment, and the test set size means the number of purchased items during the test period. Experimental test result shows the hit ratio of BC and NC is bigger than that of TC. This means using neighbors Is more effective to recommend new items. That is hybrid algorithm using CF is more effective when recommending to consumers new items than the algorithm using only CB. The reason of the smaller hit ratio of BC than that of NC is that BC is defined as a dummy or virtual customer who purchased all items of target customers' and neighbors'. That is centroid of BC often shifts from that of TC, so it tends to reflect skewed characters of target customer. So the recommendation algorithm using NC shows the best hit ratio, because NC has sufficient information about target customers and their neighbors without damaging the information about the target customers.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.179-192
• /
• 2014

Keeping in line with the recent changes in the information technology environment, the online learning environment that supports multiple users' participation such as MOOC (Massive Open Online Courses) has become important. One of the largest professional associations in Information Technology, IEEE Computer Society, announced that "Supporting New Learning Styles" is a crucial trend in 2014. Popular MOOC services, CourseRa and edX, have continued to build active learning environment with a large number of lectures accessible anywhere using smart devices, and have been used by an increasing number of users. In addition, collaborative web services (e.g., blogs and Wikipedia) also support the creation of various user-uploaded learning materials, resulting in a vast amount of new lectures and learning materials being created every day in the online space. However, it is difficult for an online educational system to keep a learner' motivation as learning occurs remotely, with limited capability to share knowledge among the learners. Thus, it is essential to understand which materials are needed for each learner and how to motivate learners to actively participate in online learning system. To overcome these issues, leveraging the constructivism theory and collective intelligence, we have developed a social bookmarking system called WeStudy, which supports learning material sharing among the users and provides personalized learning material recommendations. Constructivism theory argues that knowledge is being constructed while learners interact with the world. Collective intelligence can be separated into two types: (1) collaborative collective intelligence, which can be built on the basis of direct collaboration among the participants (e.g., Wikipedia), and (2) integrative collective intelligence, which produces new forms of knowledge by combining independent and distributed information through highly advanced technologies and algorithms (e.g., Google PageRank, Recommender systems). Recommender system, one of the examples of integrative collective intelligence, is to utilize online activities of the users and recommend what users may be interested in. Our system included both collaborative collective intelligence functions and integrative collective intelligence functions. We analyzed well-known Web services based on collective intelligence such as Wikipedia, Slideshare, and Videolectures to identify main design factors that support collective intelligence. Based on this analysis, in addition to sharing online resources through social bookmarking, we selected three essential functions for our system: 1) multimodal visualization of learning materials through two forms (e.g., list and graph), 2) personalized recommendation of learning materials, and 3) explicit designation of learners of their interest. After developing web-based WeStudy system, we conducted usability testing through the heuristic evaluation method that included seven heuristic indices: features and functionality, cognitive page, navigation, search and filtering, control and feedback, forms, context and text. We recruited 10 experts who majored in Human Computer Interaction and worked in the same field, and requested both quantitative and qualitative evaluation of the system. The evaluation results show that, relative to the other functions evaluated, the list/graph page produced higher scores on all indices except for contexts & text. In case of contexts & text, learning material page produced the best score, compared with the other functions. In general, the explicit designation of learners of their interests, one of the distinctive functions, received lower scores on all usability indices because of its unfamiliar functionality to the users. In summary, the evaluation results show that our system has achieved high usability with good performance with some minor issues, which need to be fully addressed before the public release of the system to large-scale users. The study findings provide practical guidelines for the design and development of various systems that utilize collective intelligence.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Information Systems Review
• /
• v.23 no.3
• /
• pp.51-75
• /
• 2021

Global e-commerce websites offer personalized recommendation services to gain sustainable competitiveness. Existing studies have offered personalized recommendation services using quantitative preferences such as ratings. However, offering personalized recommendation services using only quantitative data has raised the problem of decreasing recommendation performance. For example, a user gave a five-star rating but wrote a review that the user was unsatisfied with hotel service and cleanliness. In such cases, has problems where quantitative and qualitative preferences are inconsistent. Recently, a growing number of studies have considered review data simultaneously to improve the limitations of existing personalized recommendation service studies. Therefore, in this study, we identify review and rating mismatches and build a new user profile to offer personalized recommendation services. To this end, we use deep learning algorithms such as CNN, LSTM, CNN + LSTM, which have been widely used in sentiment analysis studies. And extract sentiment features from reviews and compare with quantitative preferences. To evaluate the performance of the proposed methodology in this study, we collect user preference information using real-world hotel data from the world's largest travel platform TripAdvisor. Experiments show that the proposed methodology in this study outperforms the existing other methodologies, using only existing quantitative preferences.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.159-185
• /
• 2016

Planning a multi-day trip is a complex, yet time-consuming task. It usually starts with selecting a list of points of interest (POIs) worth visiting and then arranging them into an itinerary, taking into consideration various constraints and preferences. When choosing POIs to visit, one might ask friends to suggest them, search for information on the Web, or seek advice from travel agents; however, those options have their limitations. First, the knowledge of friends is limited to the places they have visited. Second, the tourism information on the internet may be vast, but at the same time, might cause one to invest a lot of time reading and filtering the information. Lastly, travel agents might be biased towards providers of certain travel products when suggesting itineraries. In recent years, many researchers have tried to deal with the huge amount of tourism information available on the internet. They explored the wisdom of the crowd through overwhelming images shared by people on social media sites. Furthermore, trip planning problems are usually formulated as 'Tourist Trip Design Problems', and are solved using various search algorithms with heuristics. Various recommendation systems with various techniques have been set up to cope with the overwhelming tourism information available on the internet. Prediction models of recommendation systems are typically built using a large dataset. However, sometimes such a dataset is not always available. For other models, especially those that require input from people, human computation has emerged as a powerful and inexpensive approach. This study proposes CYTRIP (Crowdsource Your TRIP), a multi-day trip itinerary planning system that draws on the collective intelligence of contributors in recommending POIs. In order to enable the crowd to collaboratively recommend POIs to users, CYTRIP provides a shared workspace. In the shared workspace, the crowd can recommend as many POIs to as many requesters as they can, and they can also vote on the POIs recommended by other people when they find them interesting. In CYTRIP, anyone can make a contribution by recommending POIs to requesters based on requesters' specified preferences. CYTRIP takes input on the recommended POIs to build a multi-day trip itinerary taking into account the user's preferences, the various time constraints, and the locations. The input then becomes a multi-day trip planning problem that is formulated in Planning Domain Definition Language 3 (PDDL3). A sequence of actions formulated in a domain file is used to achieve the goals in the planning problem, which are the recommended POIs to be visited. The multi-day trip planning problem is a highly constrained problem. Sometimes, it is not feasible to visit all the recommended POIs with the limited resources available, such as the time the user can spend. In order to cope with an unachievable goal that can result in no solution for the other goals, CYTRIP selects a set of feasible POIs prior to the planning process. The planning problem is created for the selected POIs and fed into the planner. The solution returned by the planner is then parsed into a multi-day trip itinerary and displayed to the user on a map. The proposed system is implemented as a web-based application built using PHP on a CodeIgniter Web Framework. In order to evaluate the proposed system, an online experiment was conducted. From the online experiment, results show that with the help of the contributors, CYTRIP can plan and generate a multi-day trip itinerary that is tailored to the users' preferences and bound by their constraints, such as location or time constraints. The contributors also find that CYTRIP is a useful tool for collecting POIs from the crowd and planning a multi-day trip.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.67-86
• /
• 2020

Recommender Systems have been huge influence users and business more and more. Recently the importance of E-commerce has been reached rapid growth greatly in world-wide COVID-19 pandemic. Recommender system is the center of E-commerce lively. Top ranked E-commerce managers mentioned that recommender systems have a major influence on customer's purchase such as about 50% of Netflix, Amazon sales from their recommender systems. Most algorithms have been focused on improving accuracy of recommender system regardless of novelty, diversity, serendipity etc. Recommender systems with only high accuracy cannot satisfy business long-term profit because of generating sales polarization. In addition, customers do not experience enjoyment of shopping from only focusing accuracy recommender system because customer's preference is changed constantly. Therefore, recommender systems with various values need to be developed for user's high satisfaction. Reranking is the most useful methodology to realize diversity of recommender system. In this paper, diversity of recommender system is represented through constructing high similarity with users who have different preference using each user's purchased item's category algorithm. It is distinguished from past research approach which is changing the algorithm of recommender system without user's diversity preference level. We tried to discover user's diversity preference level and observed the results how the effect was different according to user's diversity preference level. In addition, graph-based recommender system was used to show diversity through user's network, not collaborative filtering. In this paper, Amazon Grocery and Gourmet Food data was used because the low-involvement product, such as habitual product, foods, low-priced goods etc., had high probability to show customer's diversity. First, a bipartite graph with users and items simultaneously is constructed to make graph-based recommender system. However, each users and items unipartite graph also need to be established to show diversity of recommender system. The weight of each unipartite graph has played crucial role changing Jaccard Distance of item's category. We can observe two important results from the user's unipartite network. First, the user's diversity preference level is observed from the network and second, dissimilar users can be discovered in the user's network. Through the research process, diversity of recommender system is presented highly with small accuracy loss and optimalization for higher accuracy is possible controlling diversity ratio. This paper has three important theoretical points. First, this research expands recommender system research for user's satisfaction with various values. Second, the graph-based recommender system is developed newly. Third, the evaluation indicator of diversity is made for diversity. In addition, recommender systems are useful for corporate profit practically and this paper has contribution on business closely. Above all, business long-term profit can be improved using recommender system with diversity and the recommender system can provide right service according to user's diversity level. Lastly, the corporate selling low-involvement products have great effect based on the results.