• KIISE Transactions on Computing Practices
• /
• v.21 no.2
• /
• pp.121-125
• /
• 2015

In recent years, research on collaborative filtering-based recommendation systems emphasized the accuracy of rating predictions, and this has led to an increase in computation time. As a result, such systems have divergeded from the original purpose of making quick recommendations. In this paper, we propose a recommendation algorithm that uses a Preference Difference Metric to reduce the computation time and to maintain adequate performance. The system recommends items according to their preference classification.

• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.439-450
• /
• 2010

In this paper, we propose a new idea to evaluate the prediction accuracy of user's preference generated by memory-based collaborative filtering algorithm before prediction process in the recommender system. Our analysis results show the possibility of a pre-evaluation before the prediction process of users' preference of item's transaction on the web. Classification functions proposed in this study generate a user's rating pattern under certain conditions. In this research, we test whether classification functions select users who have lower prediction or higher prediction performance under collaborative filtering recommendation approach. The statistical test results will be based on the differences of the prediction accuracy of each user group which are classified by classification functions using the generative probability of specific rating. The characteristics of rating patterns of classified users will also be presented.

• The Journal of the Korea Contents Association
• /
• v.7 no.11
• /
• pp.23-33
• /
• 2007

The collaborative filtering has used the nearest neighborhood method based on the preference and the similarity using the Pearson correlation coefficient. Therefore, it does not reflect content of the items and has the problems of the sparsity and scalability as well. the item-based collaborative filtering has been practically used to improve these defects, but it still does not reflect attributes of the item. In this paper, we propose the user and item based collaborative filtering using the classification property and Naive Bayesian to supplement the defects in the existing recommendation system. The proposed method complexity refers to the item similarity based on explicit data and the user similarity based on implicit data for handing the sparse problem. It applies to the Naive Bayesian to the result of reference. Also, it can enhance the accuracy as computation of the item similarity reflects on the correlative rank among the classification property to reflect attributes.

• Journal of the Korean Society of Costume
• /
• v.2
• /
• pp.73-88
• /
• 1978

This article is an attempt to explain, at least in part, the contemporary Korean women's consciousness of Western Dreasses. As time changes, the role of clothing undergoes varisous transitions, while values and ways of life are constantly in change. It is, therefore, proper and appropriate to recognize as among the major aspects of social psychology such phenomenon as interests, understanding of clothing, the choice of a dress, and attitudes toward clothing, etc. The purpose of this study is to discover problems concerning and their clothing and their solutions, by means of a surveying approach. The method of research used is based upon questionares distributed to parents of first-year pupils in elementary schools and to female clerks working in offices, covering the period from August through October, 1976. The number of the questionares distrubuted totalled 600, and 526 were returned to the research to be utilized for analysis. The contents of the survey included such things as values concerning clothing, kinds of clothing and their practical use, the selection of clothing and the method of purchase, fashions, etc. The classification of aquisition are self-made clothing, clothing made to order and ready-made materials. It is composed of 25 items, including affirmative reasons as well as negative ones. The processing of the material returned was made by using the computer, and based upon classifications such as ages, monthly income, occupations; thus diagraming the result in percentages. The conclusion made and the improvements proposed are as follows: 1. The values of clothing were placed on the expression of the wearer's personality (32.7) and on eauty(28. 6%). The lower age group places is stress upon the expression of personality, while the higher age group stresses beauty. About 50% of wearers are contented with their clothing, their clothing, the rest of whom them indicating their dissatisfaction with what they wear. As to designs at the time of selection, about 46% indicated their preference of personal expression, 31.8% on usefulness. In selecting material, practicality is emphasized; in selecting patterns, single color is preferred. In short, personal expression and esthetic values are primary, with consideration of practicality in mind. 2. The classification of clothing according to their uses indicates the highest numbers in normal wear (home wears) and clothings to be worn outside home. As to evening dresses, (party dress) only one or two articles were checked by many, and no such article was clamed to be possessed by most. The highest ratio of wearing was shown in the case of home wear (47.3%) and clothing to be worn outside the home, which is 55.8%. The budget for one article of clothing was greatest in the case of home wear, and clothing worn outside the home. Many used both kinds of articles for the same purpose. It is desirable, therefore, that the kinds of clothing should be varied according to the purpose for which they are worn, and that clothing appropriate for that purpose should be worn. 3. The motivation for purchasing clothing was highly chosen in the item of seasonal change, which was 55.7%; Clothing deliberately made was indicated by 45.2%. In the mothods of purchasing clothing, clothing made to order and ready-made was indicated by 44.4%, which is the highest; Clothing made to order was 25.4%, and self-sewing was 1.1%, which is the lowest. (1) In the case of self-sewing, "I like it but it is very hard," was checked by 43.6%; "It is so difficult that I cannot wear such clothing" was checked by 13.3%. From these, we can conclude that the questionees are willing to make clothing by themselves, but techniques involved in sewing and at her problems involved in the skill are complicated but when those problems are eliminated there is a possibility for practice. The response checked by questionees concerning the self-sewing was, "It's economical", which is a clear indication that many questionees are positive for self-sewing. It is generally believed that ready-made clothing is cheaper, but it is not necessarily so. In consideration of the quality of clothing, self-sewing is a necessity, and it is desirable that it should be encouraged. (3) Problems involved in ready-made clothing, such as designs, skills, size (fitting) should be eliminated. When these problems are scientifically gotten rid of, it is possible that affirmative returns will be expected. Affirmative responses such as "Ready-made clothing is economical," "You can select there on the spot," are good signs that many women expect to wear ready-made clothing. It is in this sense that the prospect for ready-made clothing is brighter when much development for ready-made clothing is on the way. 4. Much concern for fashion are checked in such item of questions as "Fashionable clothing in the show window," "Clothes worn by women." The first item was checked by 50.1 %, and the second was checked by 48.6%. The reason for following fashion is "Because many people wear them," which was indicated by 30.4%. The reason for not following fashion is "It is too expensive," which was checked by 29.6%. The 26.2% of the answers indicated that "Fashionable clothing is devoid of personality," The influences of fashion over the development of fashion over the development of clothing are two-fold: Esthetic and active. It is not to be deniable that people follow fashion more or less. 1978.9>

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.