• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.93-100
• /
• 2022

In the era of information overload on the Internet, the recommendation system, which is an indispensable function, is a service that recommends products that a user may prefer, and has been successfully provided in various commercial sites. Recently, studies to reflect the rating time of items to improve the performance of collaborative filtering, a representative recommendation technique, are active. The core idea of these studies is to generate the recommendation list by giving an exponentially lower weight to the items rated in the past. However, this has a disadvantage in that a time function is uniformly applied to all items without considering changes in users' preferences according to the characteristics of the items. In this study, we propose a time-aware collaborative filtering technique from a completely different point of view by developing a new similarity measure that integrates the change in similarity values between items over time into a weighted sum. As a result of the experiment, the prediction performance and recommendation performance of the proposed method were significantly superior to the existing representative time aware methods and traditional methods.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.149-155
• /
• 2022

The popularity of e-commerce systems on the Internet is increasing day by day, and the recommendation system, as a core function of these systems, greatly reduces the effort to search for desired products by recommending products that customers may prefer. The collaborative filtering technique is a recommendation algorithm that has been successfully implemented in many commercial systems, but despite its popularity and usefulness in academia, the memory-based implementation has inaccuracies in its reference neighbor. To solve this problem, this study proposes a new time-aware collaborative filtering technique that integrates and utilizes the neighbors of each item and each user, weighting the recent similarity more than the past similarity with them, and reflecting it in the recommendation list decision. Through the experimental evaluation, it was confirmed that the proposed method showed superior performance in terms of prediction accuracy than other existing methods.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.75-82
• /
• 2023

In collaborative filtering systems, the item rating prediction values calculated by the systems are very important for customer satisfaction with the recommendation list. In the time-aware system, predictions are calculated by reflecting the rating time of users, and in general, exponentially lower weights are assigned to past rating values. In this study, to find out whether the influence of rating time on the rating value varies according to various factors, the correlation between user rating value and rating time is investigated by the degree of user rating activity, the popularity of items, and item genres. As a result, using two types of public datasets, especially in the sparse dataset, significantly different correlation index values were obtained for each factor. Therefore, it is confirmed that the influence weight of the rating time on the rating prediction value should be set differently in consideration of the above-mentioned various factors as well as the density of the dataset.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• The Journal of the Korea Contents Association
• /
• v.8 no.2
• /
• pp.1-8
• /
• 2008

The information system in which users can utilize to control and to get the filtered information efficiently has appeared. Content-based filtering can reflect content information, and it provides recommendation by comparing the feature information about item and the profile of preference. This has the shortcoming of the varying accuracy of prediction depending on teaming method. This paper suggests the discovery of preference through learning the profile for the content-based filtering. This study improves the accuracy of recommendation through learning the profile according to granting the preference of 6 levels to estimated value in order to solve the problem. Finally, to evaluate the performance of the proposed method, this study applies to MovieLens dataset, and it is compared with the performance of previous studies.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.1-17
• /
• 2023

With the recent rapid development of ICT(Information and Communication Technology) and the popularization of digital devices, the size of the online market continues to grow. As a result, we live in a flood of information. Thus, customers are facing information overload problems that require a lot of time and money to select products. Therefore, a personalized recommender system has become an essential methodology to address such issues. Collaborative Filtering(CF) is the most widely used recommender system. Traditional recommender systems mainly utilize quantitative data such as rating values, resulting in poor recommendation accuracy. Quantitative data cannot fully reflect the user's preference. To solve such a problem, studies that reflect qualitative data, such as review contents, are being actively conducted these days. To quantify user review contents, text mining was used in this study. The general CF consists of the following three steps: user-item matrix generation, Top-N neighborhood group search, and Top-K recommendation list generation. In this study, we propose a recommendation algorithm that applies an extended similarity measure, which utilize quantified review contents in addition to user rating values. After calculating review similarity by applying TF-IDF, Word2Vec, and Doc2Vec techniques to review content, extended similarity is created by combining user rating similarity and quantified review contents. To verify this, we used user ratings and review data from the e-commerce site Amazon's "Health and Personal Care". The proposed recommendation model using extended similarity measure showed superior performance to the traditional recommendation model using only user rating value-based similarity measure. In addition, among the various text mining techniques, the similarity obtained using the TF-IDF technique showed the best performance when used in the neighbor group search and recommendation list generation step.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.27-42
• /
• 2020

Traditional companies with offline stores were unable to secure large display space due to the problems of cost. This limitation inevitably allowed limited kinds of products to be displayed on the shelves, which resulted in consumers being deprived of the opportunity to experience various items. Taking advantage of the virtual space called the Internet, online shopping goes beyond the limits of limitations in physical space of offline shopping and is now able to display numerous products on web pages that can satisfy consumers with a variety of needs. Paradoxically, however, this can also cause consumers to experience the difficulty of comparing and evaluating too many alternatives in their purchase decision-making process. As an effort to address this side effect, various kinds of consumer's purchase decision support systems have been studied, such as keyword-based item search service and recommender systems. These systems can reduce search time for items, prevent consumer from leaving while browsing, and contribute to the seller's increased sales. Among those systems, recommender systems based on association rule mining techniques can effectively detect interrelated products from transaction data such as orders. The association between products obtained by statistical analysis provides clues to predicting how interested consumers will be in another product. However, since its algorithm is based on the number of transactions, products not sold enough so far in the early days of launch may not be included in the list of recommendations even though they are highly likely to be sold. Such missing items may not have sufficient opportunities to be exposed to consumers to record sufficient sales, and then fall into a vicious cycle of a vicious cycle of declining sales and omission in the recommendation list. This situation is an inevitable outcome in situations in which recommendations are made based on past transaction histories, rather than on determining potential future sales possibilities. This study started with the idea that reflecting the means by which this potential possibility can be identified indirectly would help to select highly recommended products. In the light of the fact that the attributes of a product affect the consumer's purchasing decisions, this study was conducted to reflect them in the recommender systems. In other words, consumers who visit a product page have shown interest in the attributes of the product and would be also interested in other products with the same attributes. On such assumption, based on these attributes, the recommender system can select recommended products that can show a higher acceptance rate. Given that a category is one of the main attributes of a product, it can be a good indicator of not only direct associations between two items but also potential associations that have yet to be revealed. Based on this idea, the study devised a recommender system that reflects not only associations between products but also categories. Through regression analysis, two kinds of associations were combined to form a model that could predict the hit rate of recommendation. To evaluate the performance of the proposed model, another regression model was also developed based only on associations between products. Comparative experiments were designed to be similar to the environment in which products are actually recommended in online shopping malls. First, the association rules for all possible combinations of antecedent and consequent items were generated from the order data. Then, hit rates for each of the associated rules were predicted from the support and confidence that are calculated by each of the models. The comparative experiments using order data collected from an online shopping mall show that the recommendation accuracy can be improved by further reflecting not only the association between products but also categories in the recommendation of related products. The proposed model showed a 2 to 3 percent improvement in hit rates compared to the existing model. From a practical point of view, it is expected to have a positive effect on improving consumers' purchasing satisfaction and increasing sellers' sales.

• Journal of Advanced Navigation Technology
• /
• v.18 no.5
• /
• pp.468-475
• /
• 2014

The recommend system is getting more difficult real time recommend by lager preference data set, computing power and recommend algorithm. For this reason, recommend system is proceeding actively one's studies toward distribute processing method of large preference data set. This paper studied distribute processing method of large preference data set using hadoop distribute processing platform and mahout machine learning library. The recommend algorithm is used Co-occurrence Matrix similar to item Collaborative Filtering. The Co-occurrence Matrix can do distribute processing by many node of hadoop cluster, and it needs many computation scale but can reduce computation scale by distribute processing. This paper has simplified distribute processing of co-occurrence matrix by changes over from four stage to three stage. As a result, this paper can reduce mapreduce job and can generate recommend file. And it has a fast processing speed, and reduce map output data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.1
• /
• pp.87-92
• /
• 2021

Bias, variance, error and learning are important factors for performance in modeling a big data based recommendation system. The recommendation model in this system must reduce complexity while maintaining the explanatory diagram. In addition, the sparsity of the dataset and the prediction of the system are more likely to be inversely proportional to each other. Therefore, a product recommendation model has been proposed through learning the similarity between products by using a factorization method of the sparsity of the dataset. In this paper, the generalization ability of the model is improved by applying the max-norm regularization as an optimization method for the loss function of this model. The solution is to apply a stochastic projection gradient descent method that projects a gradient. The sparser data became, it was confirmed that the propsed regularization method was relatively effective compared to the existing method through lots of experiment.

• The KIPS Transactions:PartD
• /
• v.16D no.2
• /
• pp.273-280
• /
• 2009

Today, many services and products that used to be only provided on offline have been being provided on the web according to the improvement of computing environment and the activation of web usage. These web-based services and products tend to be provided to customer by customer's preferences. This paradigm that considers customer's opinions and features in selecting is called personalization. The related research field is a recommendation. And this recommendation is performed by recommender system. Generally the recommendation is made from the preferences and tastes of customers. And recommender system provides this recommendation to user. However, the recommendation techniques have a couple of problems; they do not provide suitable recommendation to new users and also are limited to computing space that they generate recommendations which is dependent on ratings of products by users. Those problems has gathered some continuous interest from the recommendation field. In the case of new users, so similar users can't be classified because in the case of new users there is no rating created by new users. The problem of the limitation of the recommendation space is not easy to access because it is related to moneywise that the cost will be increasing rapidly when there is an addition to the dimension of recommendation. Therefore, I propose the solution of the recommendation problem of new user and the usage of item quality as weight to improve the accuracy of recommendation in this paper.