초록
기존 협업 필터링 기법은 사용자들의 아이템에 대한 선호도를 기반으로 유사 아이템 집합 또는 유사 사용자 집합을 구성하고, 이를 이용해 예측된 사용자의 특정 아이템에 대한 선호도를 기반으로 추천을 수행한다. 이로 인해, 사용자 선호도 정보가 부족하게 되면, 유사 아이템 사용자 집합의 신뢰도가 낮아지고, 추천 서비스의 신뢰도 또한 따라서 낮아진다. 또한, 서비스의 규모가 커질수록, 유사 아이템, 사용자 집합의 생성에 걸리는 시간은 기하급수적으로 증가하고 추천서비스의 응답시간 또한 그에 따라 증가하게 된다. 위와 같은 문제점을 해결하기 위해 본 논문에서는 적응형 군집화 기법을 제안하고 이를 적용한 협업 필터링 기법을 제안하고 있다. 이 기법은 크게 네 가지 방법으로 이루어진다. 첫째, 사용자와 아이템의 특성 벡터를 기반으로 사용자와 아이템 각각을 군집화 하여, 기존 협업 필터링 기법에서 유사 아이템, 사용자 집합을 생성하는데 소요되는 시간을 절약하며, 사용자 선호도 정보만을 이용한 부분 집합 생성보다 추천의 신뢰도를 높이고, 초기 평가 문제와 초기 이용자 문제를 일부 해소한다. 둘째, 미리 구성된 사용자와 아이템의 군집을 기반으로 군집간의 선호도를 이용해 추천을 수행한다. 사용자가 속한 군집의 선호도가 높은 순서대로 아이템 군집을 조회하여 사용자에게 제공할 아이템 목록을 구성하여, 추천 시스템의 부하 대부분을 모델 생성 단계에서 부담하고 실제 수행 시 부하를 최소화한다. 셋째, 누락된 사용자 선호도 정보를 사용자와 아이템 군집을 이용하여 예측함으로써 협업 필터링 추천 기법의 사용자 선호도 정보 희박성으로 인한 문제를 해소한다. 넷째, 사용자와 아이템의 특성 벡터를 사용자의 피드백에 따라 학습시켜 아이템과 사용자의 정성적 특성 정량화의 어려움을 해결한다. 본 연구의 검증은 기존에 제안되었던 하이브리드 필터링 기법들과의 성능 비교를 통해 이루어졌으며, 평가 방법으로는 평균 절대 오차와 응답 시간을 이용하였다.
An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.
