Collaborative Filtering Recommendation Based on All-Weighted Matrix Factorization and Fast Optimization

Li, Hongmei; Diao, Xingchun; Cao, Jianjun; Zheng, Qibin

doi:10.1109/access.2018.2828401

Cited by 32 publications

(18 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assuming some relationships have more weight compared to others, a  weight factor is added to the MRMF model. The objective function thus becomes [24] [36] [37]:…”

Section: Weighted Multi-relational Matrix Factorization Methods (Wmmentioning

confidence: 99%

Multi Relational and Social Influence Model for Predicting Student Performance in Intelligent Tutoring Systems ITS

Assielou,

Haba,

Kadjo

et al. 2020

IJEAT

View full text Add to dashboard Cite

Recent studies have shown that Matrix Factorization (MF) method, deriving from recommendation systems, can predict student performance as part of Intelligent Tutoring Systems (ITS). In order to improve the accuracy of this method, we hypothesize that taking into account the mutual influence effect in the relations of student groups would be a major asset. This criterion, coupled with those of the different relationships between the students, the tasks and the skills, would thus be essential elements for a better performance prediction in order to make personalized recommendations in the ITS. This paper proposes an approach for Predicting Student Performance (PSP) that integrates not only friendship relationships such as workgroup relationships, but also mutual influence values into the Weighted Multi-Relational Matrix Factorization method. By applying the Root Mean Squared Error (RMSE) metric to our model, experimental results from KDD Challenge 2010 database show that this approach allows to refine student performance prediction accuracy.

show abstract

“…Assuming some relationships have more weight compared to others, a  weight factor is added to the MRMF model. The objective function thus becomes [24] [36] [37]:…”

Section: Weighted Multi-relational Matrix Factorization Methods (Wmmentioning

confidence: 99%

Multi Relational and Social Influence Model for Predicting Student Performance in Intelligent Tutoring Systems ITS

Assielou,

Haba,

Kadjo

et al. 2020

IJEAT

View full text Add to dashboard Cite

show abstract

“…In [16], the authors proposed the discrete factorization machine (DFM)-based model to achieve efficient and accurate performance of the recommendation system by minimizing quantization loss for a large number of feature dimensions. In [35], the authors proposed an effective and efficient recommendation framework with the all-weighted scheme and fast optimization scheme. They designed a learning algorithm based on the elementwise alternating least squares (eALS) technique to efficiently optimize a matrix factorization (MF) model with variably weighted missing data.…”

Section: Recommendation In Online Broadcastingmentioning

confidence: 99%

Tree-Based Real-Time Advertisement Recommendation System in Online Broadcasting

2020

View full text Add to dashboard Cite

The viewing time of media content per week through TV is still dominant. Users are exposed to numerous advertisements, such as commercials, electronic home shopping, product placement (PPL), and T-Commerce while watching TV programs. Most of the advertisement systems provide a good overview of products. However, traditional advertising services do not consider user preferences, meaning it is difficult to expect anything more than mere exposure to them. We can adopt a recommendation system to predict the preference. However, existing recommendation systems find it difficult to satisfy the realtime requirements of online broadcasting because of the large overhead incurred in preference prediction processes. In this paper, we propose a real-time recommendation system to provide personalized advertisements. The proposed system generates tree models based on user historical data. To reduce the overhead of preference prediction, we introduce a sorted HashMap that enables fast tree searches. For sophisticated preference prediction, the proposed system normalizes the users' preferences by considering the characteristics of their tree model. Finally, we conduct experiments to evaluate the performance of the proposed tree-based recommendation system.

show abstract

“…Using social relations incorporate virtual ratings into the historical ratings of the users who have insufficient ratings can improve the performance of the rating prediction process [4]. The traditional recommendation algorithm is mainly divided into collaborative filtering [5]- [9] and content-based recommendation [10]- [13] tasks. Collaborative filtering is highly dependent on user activity, and it is difficult to manage items without a sufficient number of user ratings, resulting in the so-called cold-start problem [14], [15].Trust-aware recommender systems can alleviate cold start and data sparsity problems in recommendation methods through trust relations [16], [17].…”

Section: Related Workmentioning

confidence: 99%

Dtree2vec: A High-Accuracy and Dynamic Scheme for Real-Time Book Recommendation by Serialized Chapters and Local Fine-Grained Partitioning

Zhao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the rapid development of social computing technologies and online reading platforms, the proportion of e-books, especially online serialized novels, has been increasing. Identifying ways to add updated serialized books to readers' real-time recommendation lists has become an urgent problem to be solved. While serialized books are still underwritten and in the process of production, their features and categories can constantly evolve and change, lacking complete text content information and complete global scoring data. Therefore, this paper proposes a dynamic DTree2Vec scheme for serialized books that models text of varying degrees of completion to achieve unified semantic feature representation to measure the semantic relevance of books. At the same time, it ensures recommendation quality by tracking the update status of serialized books and by adding the subsequent chapter content in real time. This scheme establishes a dynamic hierarchical tree structure for serialized books and applies a cosine-type local reconstruction model to reconstruct new semantic features of books. In addition, the fine-grained factor of chapter partitioning is introduced to the reconstruction process to adjust the proportion of global and local features to better represent the semantic features of books. We analyzed effects of the content of serialized chapters on the recommendation results and used semantic features of the reconstruction to represent the content of serial novels in real time. The experiment results prove that the proposed DTree2Vec scheme can achieve higher degrees of recommendation accuracy when dealing with unfinished serialized books, effectively alleviating dynamic capture problems and real-time recommendations of book recommendations.

show abstract

Collaborative Filtering Recommendation Based on All-Weighted Matrix Factorization and Fast Optimization

Cited by 32 publications

References 26 publications

Multi Relational and Social Influence Model for Predicting Student Performance in Intelligent Tutoring Systems ITS

Multi Relational and Social Influence Model for Predicting Student Performance in Intelligent Tutoring Systems ITS

Tree-Based Real-Time Advertisement Recommendation System in Online Broadcasting

Dtree2vec: A High-Accuracy and Dynamic Scheme for Real-Time Book Recommendation by Serialized Chapters and Local Fine-Grained Partitioning

Contact Info

Product

Resources

About