No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Case-Based Reasoning for Personalized Recommender on User Preference through Dynamic Clustering
... In the recommendation process, it calculates the recommendation score through the linear combination of emotional features and similarity, which is used for query-based and user-based recommendation scenarios. Li et al. [122] argued that, since users only interact with items of interest in the recommendation system, that system must retain very large amounts of personalized information and item sparsity, which seriously affects the performance of the recommendation system; therefore, they proposed a CBRrecommender method to reduce data sparsity through data classification and dynamic clustering, which makes the system run faster in large-scale recommendation research that dynamically calculates user preferences. ...
... In the recommendation process, it calculates the recommendation score through the linear combination of emotional features and similarity, which is used for query-based and user-based recommendation scenarios. Li et al. [122] argued that, since users only interact with items of interest in the recommendation system, that system must retain very large amounts of personalized information and item sparsity, which seriously affects the performance of the recommendation system; therefore, they proposed a CBR-recommender method to reduce data sparsity through data classification and dynamic clustering, which makes the system run faster in large-scale recommendation research that dynamically calculates user preferences. ...
Case-based reasoning (CBR), which is based on the cognitive assumption that similar problems have similar solutions, is an important problem-solving and learning method in the field of artificial intelligence (AI). In this article, the development of CBR is reviewed, and the major challenges of CBR are summarized. The paper is organized into four parts. First, the basic framework and concepts of CBR are introduced. Then, the developed technology and innovative work that were designed to solve problems by CBR are summarized. Then, the application fields of CBR are summarized. Finally, according to the idea of deep learning and interpretable AI, the main challenges for the future development of CBR are proposed.
The real estate industry has increasingly leveraged the Internet as a significant transaction platform, yet it needs to improve in optimizing search efficiency and offering intuitive results for homebuyers. This study addresses these challenges by developing a comprehensive Real Estate Management Platform and Dynamic Scoring System to enhance the property search process by integrating a user-oriented recommender system with a multi-layered architecture. The system includes a User Interface, a Business Logic Layer incorporating APIs, algorithms, business rules, external services such as Google Maps, Foursquare, Walkscore, Greatschools, and Yelp, and a Database Layer. The platform mirrors real-world purchasing decisions by dynamically ranking search criteria through a scalable and precise value assessment mechanism, significantly improving search efficiency. The system architecture ensures scalability, security, and seamless user interactions with advanced features such as a map-based interface, geospatial data integration, preference-organized sets, and consultant and scheduling interfaces. User testing demonstrates the system's effectiveness in streamlining the real estate search process and providing accurate and personalized recommendations.
In the past two decades, recommender systems have been successfully applied in many e-commerce companies. One of the promising techniques to generate personalized recommendations is collaborative filtering. However, it suffers from sparsity problem. Alleviating this problem, cross-domain recommender systems came into existence in which transfer learning mechanism is applied to exploit the knowledge from other related domains. While applying transfer learning, some information should overlap between source and target domains. Several attempts have been made to enhance the performance of collaborative filtering with the help of other related domains in cross-domain recommender systems framework. Although exploiting the knowledge from other domains is still challenging and open problem in recommender systems. In this paper, we propose a method namely User Profile as a Bridge in Cross-domain Recommender Systems (UP-CDRSs) for transferring knowledge between domains through user profile. Firstly, we build a user profile using demographical information of a user, explicit ratings and content information of user-rated items. Thereafter, the probabilistic graphical model is employed to learn latent factors of users and items in both domains by maximizing posterior probability. At last prediction on unrated item is estimated by an inner product of corresponding latent factors of users and items. Validating of our proposed UP-CDRSs method, we conduct series of experiments on various sparsity levels using cross-domain dataset. The results demonstrate that our proposed method substantially outperforms other without and with transfer learning methods in terms of accuracy.
Collaborative filtering (CF) has been generally used in recommender systems when faced some practical problems. Due to the sparsity of rating matrix, the traditional CF-based approach has a significant decline in recommendation performance. Gradually, a hybrid method that using side information and rating information has been widely employed and achieves great performance. Together with side information and rating information, the hybrid method can overcome the data sparsity and cold-start problems. However, they seem to fail to take into account the fact that the sparsity of single side information. To solve this problem, we take full advantage of the characteristics of deep learning that can learn effective representation and propose a novel deep learning model named additional variational autoencoder (AVAE) that considers both item content and tag information. The model learns effective latent representations from additional side information including content information and tag information in an unsupervised manner. With the help of graphical models, it can extract the implicit relationships between users and items effectively. A large number of experimental results on two actual datasets show that our proposed model is superior to other methods and performance improvement is achieved.
Attribute Weights Assignment is an important method to solve real world problems full of uncertainty, for it is difficult to acquire a comprehensive formula theoretically with which so many empirical calculations have to be drilled out of domain experts. Case-Intelligent System based on CBR (case-based reasoning), which is a human creative thinking and useful reasoning model for problem-solving, can acquire prior knowledge from the former stored cases implicating decision strategy empirical and powerful, and construct a flexible system integrated with efficient machine learning methods coping with uncertainty. Attribute weights also are the key for case similarity measurement and optimal case selection in CBR cycle, so the similarity Rough Sets is proposed for case attributes reduction, knowledge obtainment and objective weights acquiring in our case-intelligent system, which performs well in real experiments on decision-making and achieves reasonable explanations.
A key issue in group recommendation is how to combine the individual preferences of different users that form a group and elicit a profile that accurately reflects the tastes of all members in the group. Most Group Recommender Systems (GRSs) make use of some sort of method for aggregating the preference models of individual users to elicit a recommendation that is satisfactory for the whole group. In general, most GRSs offer good results, but each of them have only been tested in one application domain.This paper describes a domain-independent GRS that has been used in two different application domains. In order to create the group preference model, we select two techniques that are widely used in other GRSs and we compare them with two novel techniques. Our aim is to come up with a model that weighs the preferences of all the individuals to the same extent in such a way that no member in the group is particularly satisfied or dissatisfied with the final recommendations.
Let M be an n¿ à n matrix of rank r, and assume that a uniformly random subset E of its entries is observed. We describe an efficient algorithm, which we call OptSpace, that reconstructs M from |E| = O(rn) observed entries with relative root mean square error 1/2 RMSE ¿ C(¿) (nr/|E|)1/2 with probability larger than 1 - 1/n3. Further, if r = O(1) and M is sufficiently unstructured, then OptSpace reconstructs it exactly from |E| = O(n log n) entries with probability larger than 1 - 1/n3. This settles (in the case of bounded rank) a question left open by Candes and Recht and improves over the guarantees for their reconstruction algorithm. The complexity of our algorithm is O(|E|r log n), which opens the way to its use for massive data sets. In the process of proving these statements, we obtain a generalization of a celebrated result by Friedman-Kahn-Szemeredi and Feige-Ofek on the spectrum of sparse random matrices.
Recommender Systems are a subclass of information filtering systems that seek to predict the preferences of a user or the preference that a user would give to an item. The most common problem faced by these systems is the lack of data. Such a situation leads to a matrix that is extremely sparse thus reducing the accuracy of prediction. Cold-start problem is one such problem that is faced by the recommender systems when a new user or a new item enters the system. We are hoping to reduce the cold-user and the cold-item problem by reducing the sparsity of the sparse matrix with the help of Iterative Local Least Squares algorithm and a hybrid of Heat Spreading algorithm and Probability Spreading algorithm.
Though the research in personalized recommendation systems has become widespread for recent years, IEEE Internet Computing points out that current system can not meet the real large-scale e-commerce demands, and has some weakness such as low precision and slow reaction. We have proposed a structure of personalized recommendation system based on case intelligence, which originates from human experience learning, and can facilitate to integrate various artificial intelligence components. Addressing on user case retrieval problem, the paper uses constructive and understandable multi-layer feed-forward neural networks (MFNN), and employs covering algorithm to decrease the complexity of ANN algorithm. Testing from the two different domains, our experimental results indicate that the integrated method is feasible for the processing of vast and high dimensional data, and can improve the recommendation quality and support the users effectively. The paper finally signifies that the better performance mainly comes from the reliable constructing MFNN.
Capturing and understanding user interests is an important part of social media analytics. Users of social media sites often belong to multiple interest communities, and their interests are constantly changing over time. Therefore, modeling and predicting dynamic user interests poses great challenges to providing personalized recommendations in social media analytics research. We propose a novel solution to this research problem by developing a temporal overlapping community detection method based on time-weighted association rule mining. We conducted experiments using MovieLens and Netflix datasets, and our experimental results show that our proposed approach outperforms several existing methods in recommendation precision and diversity.
Recent advances in mobile devices and their sensing capabilities have enabled the collection of rich contextual information and mobile device usage records through the device logs. These context-rich logs open a venue for mining the personal preferences of mobile users under varying contexts and thus enabling the development of personalized context-aware recommendation and other related services, such as mobile online advertising. In this article, we illustrate how to extract personal context-aware preferences from the context-rich device logs, or context logs for short, and exploit these identified preferences for building personalized context-aware recommender systems. A critical challenge along this line is that the context log of each individual user may not contain sufficient data for mining his or her context-aware preferences. Therefore, we propose to first learn common context-aware preferences from the context logs of many users. Then, the preference of each user can be represented as a distribution of these common context-aware preferences. Specifically, we develop two approaches for mining common context-aware preferences based on two different assumptions, namely, context-independent and context-dependent assumptions, which can fit into different application scenarios. Finally, extensive experiments on a real-world dataset show that both approaches are effective and outperform baselines with respect to mining personal context-aware preferences for mobile users.
The participation of a node in more than one community is a common phenomenon in complex networks. However most existing methods, fail to identify nodes with multiple community affiliation, correctly. In this paper, a unique method to define overlapping community in complex networks is proposed, using the overlapping neighborhood ratio to represent relations between nodes. Matrix factorization is then utilized to assign nodes into their corresponding community structures. Moreover, the proposed method demonstrates the use of Perron clusters to estimate the number of overlapping communities in a network. Experimental results in real and artificial networks show, with great accuracy, that the proposed method succeeds to recover most of the overlapping communities existing in the network.
A new recommendation method was presented based on memetic algorithm-based clustering. The proposed method was tested on four highly sparse real-world datasets. Its recommendation performance is evaluated and compared with that of the frequency-based, user-based, item-based, k-means clustering-based, and genetic algorithm-based methods in terms of precision, recall, and F1 score. The results show that the proposed method yields better performance under the new user cold-start problem when each of new active users selects only one or two items into the basket. The average F1 scores on all four datasets are improved by 225.0%, 61.6%, 54.6%, 49.3%, 28.8%, and 6.3% over the frequency-based, user-based, item-based, k-means clustering-based, and two genetic algorithm-based methods, respectively.
The problem of point of interest (POI) recommendation is to provide personalized recommendations of places of interests, such as restaurants, for mobile users. Due to its complexity and its connection to location based social networks (LBSNs), the decision process of a user choose a POI is complex and can be influenced by various factors, such as user preferences, geographical influences, and user mobility behaviors. While there are some studies on POI recommendations, it lacks of integrated analysis of the joint effect of multiple factors. To this end, in this paper, we propose a novel geographical probabilistic factor analysis framework which strategically takes various factors into consideration. Specifically, this framework allows to capture the geographical influences on a user's check-in behavior. Also, the user mobility behaviors can be effectively exploited in the recommendation model. Moreover, the recommendation model can effectively make use of user check-in count data as implicity user feedback for modeling user preferences. Finally, experimental results on real-world LBSNs data show that the proposed recommendation method outperforms state-of-the-art latent factor models with a significant margin.
Recommender systems are becoming increasingly important to individual users and businesses for providing personalized recommendations. However, while the majority of algorithms proposed in recommender systems literature have focused on improving recommendation accuracy (as exemplified by the recent Netflix Prize competition), other important aspects of recommendation quality, such as the diversity of recommendations, have often been overlooked. In this paper, we introduce and explore a number of item ranking techniques that can generate recommendations that have substantially higher aggregate diversity across all users while maintaining comparable levels of recommendation accuracy. Comprehensive empirical evaluation consistently shows the diversity gains of the proposed techniques using several real-world rating datasets and different rating prediction algorithms.