• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.99-114
• /
• 2011

Collaborative Filtering (CF) suffers from two major problems:sparsity and cold-start recommendation. This paper focuses on the cold-start problem for new customers with no purchase records and the sparsity problem for the customers with very few purchase records. For the purpose, we propose a method for the new customer recommendation by using a combined measure based on three well-used centrality measures to identify the customers who are most likely to become neighbors of the new customer. To alleviate the sparsity problem, we also propose a hybrid approach that applies our method to customers with very few purchase records and CF to the other customers with sufficient purchases. To evaluate the effectiveness of our method, we have conducted several experiments using a data set from a department store in Korea. The experiment results show that the combination of two measures makes better recommendations than not only a single measure but also the best-seller-based method and that the performance is improved when applying the hybrid approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2399-2413
• /
• 2021

A recommendation system is an information filter tool, which uses the ratings and reviews of users to generate a personalized recommendation service for users. However, the cold-start problem of users and items is still a major research hotspot on service recommendations. To address this challenge, this paper proposes a high-efficient hybrid recommendation system based on Fuzzy C-Means (FCM) clustering and supervised learning models. The proposed recommendation method includes two aspects: on the one hand, FCM clustering technique has been applied to the item-based collaborative filtering framework to solve the cold start problem; on the other hand, the content information is integrated into the collaborative filtering. The algorithm constructs the user and item membership degree feature vector, and adopts the data representation form of the scoring matrix to the supervised learning algorithm, as well as by combining the subjective membership degree feature vector and the objective membership degree feature vector in a linear combination, the prediction accuracy is significantly improved on the public datasets with different sparsity. The efficiency of the proposed system is illustrated by conducting several experiments on MovieLens dataset.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.752-770
• /
• 2019

The purpose of this study is to incorporate telemarketing processes to improve telemarketing performance. For this application, we have attempted to mix the model of machine learning to extract potential customers with personalisation techniques to derive recommended products from actual contact. Most of traditional recommendation systems were mainly in ways such as collaborative filtering, which predicts items with a high likelihood of future purchase, based on existing purchase transactions or preferences for products. But, under these systems, new users or items added to the system do not have sufficient information, and generally cause problems such as a cold start that can not obtain satisfactory recommendation items. Also, indiscriminate telemarketing attempts can backfire as they increase the dissatisfaction and fatigue of customers who do not want to be contacted. To this purpose, this study presented a multi-purpose hybrid recommendation algorithm to achieve two goals: to select customers with high possibility of contact, and to recommend products to selected customers. In addition, we used subscription data from telemarketing agency that handles insurance products to derive realistic applicability of the proposed recommendation system. Our proposed recommendation system would certainly solve the cold start and scarcity problem of existing recommendation algorithm by using contents information such as customer master information and telemarketing history. Also. the model could show excellent performance not only in terms of overall performance but also in terms of the recommendation success rate of the unpopular product.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.494-507
• /
• 2020

This study proposed the movie recommendation system based on the user's personal information and movies rated using the method of k-clique and normalized discounted cumulative gain. The main idea is to solve the problem of cold-start and to increase the accuracy in the recommendation system further instead of using the basic technique that is commonly based on the behavior information of the users or based on the best-selling product. The personal information of the users and their relationship in the social network will divide into the various community with the help of the k-clique method. Later, the ranking measure method that is widely used in the searching engine will be used to check the top ranking movie and then recommend it to the new users. We strongly believe that this idea will prove to be significant and meaningful in predicting demand for new users. Ultimately, the result of the experiment in this paper serves as a guarantee that the proposed method offers substantial finding in raw data sets by increasing accuracy to 87.28% compared to the three most successful methods used in this experiment, and that it can solve the problem of cold-start.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1163-1185
• /
• 2024

With the sharp increase in the volume of literature data, researchers must spend considerable time and energy locating desired papers. A paper recommendation is the means necessary to solve this problem. Unfortunately, the large amount of data combined with sparsity makes personalizing papers challenging. Traditional matrix decomposition models have cold-start issues. Most overlook the importance of information and fail to consider the introduction of noise when using side information, resulting in unsatisfactory recommendations. This study proposes a paper recommendation method (PR-SLSMF) using document-level representation learning with citation-informed transformers (SPECTER) and low-rank and sparse matrix factorization; it uses SPECTER to learn paper content representation. The model calculates the similarity between papers and constructs a weighted heterogeneous information network (HIN), including citation and content similarity information. This method combines the LSMF method with HIN, effectively alleviating data sparsity and cold-start issues and avoiding topic drift. We validated the effectiveness of this method on two real datasets and the necessity of adding side information.

• 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.

• Journal of KIISE:Software and Applications
• /
• v.32 no.6
• /
• pp.542-553
• /
• 2005

Recommendation systems analyze user preferences and recommend items to a user by predicting the user's preference for those items. Among various kinds of recommendation methods, collaborative filtering(CF) has been widely used and successfully applied to practical applications. However, collaborative filtering has two inherent problems: data sparseness and the cold-start problems. If there are few known preferences for a user, it is difficult to find many similar users, and therefore the performance of recommendation is degraded. This problem is more serious when a new user is first using the system. In this paper we propose a method of integrating additional feature information of users and items into CF to overcome the difficulties caused by sparseness and improve the accuracy of recommendation. In our method, we first fill in unknown preference values by using the probability distribution of feature values, then generate the top-N recommendations by applying collaborative filtering on the modified data. We call this method of filling unknown preference values as data blurring. Several experimental results that show the effectiveness of the proposed method are also presented.

• Journal of KIISE
• /
• v.43 no.11
• /
• pp.1188-1200
• /
• 2016

Recommendation systems play a significant role in providing personalized information to users, with enhanced satisfaction and reduced information overload. Since the mid-1990s, many studies have been conducted on recommendation systems, but few have examined the recommendations of information from people in the online social networking environment. In this paper, we present a hybrid recommendation method that combines both the traditional system of content-based techniques to improve specialization, and the recently developed system of social network-based techniques to best overcome a few limitations of the traditional techniques, such as the cold-start problem. By suggesting a state-of-the-art method, this research will help users in online social networks view more personalized information with less effort than before.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.953-964
• /
• 2006

Due to the usefulness of the collaborative filtering, it has been widely used in both the research and commercial field. However, there are still some challenges for it to be more efficient, especially the scalability problem, the sparsity problem and the cold start problem. In this paper. we address these problems and provide a novel distributed approach based on agents collaboration for the problems. We have tried to solve the scalability problem by making each agent save its users ratings and broadcast them to the users friends so that only friends ratings and his own ratings are kept in an agents local database. To reduce quality degradation of recommendation caused by the lack of rating data, we introduce a method using friends opinions instead of real rating data when they are not available. We also suggest a collaborative filtering algorithm based on user profile to provide new users with recommendation service. Experiments show that our suggested approach is helpful to the new user problem as well as is more scalable than traditional centralized CF filtering systems and alleviate the sparsity problem.