rating prediction
Recently Published Documents


TOTAL DOCUMENTS

391
(FIVE YEARS 193)

H-INDEX

21
(FIVE YEARS 4)

Information ◽  
2022 ◽  
Vol 13 (1) ◽  
pp. 21
Author(s):  
Jianfei Li ◽  
Yongbin Wang ◽  
Zhulin Tao

In recent years, graph neural networks (GNNS) have been demonstrated to be a powerful way to learn graph data. The existing recommender systems based on the implicit factor models mainly use the interactive information between users and items for training and learning. A user–item graph, a user–attribute graph, and an item–attribute graph are constructed according to the interactions between users and items. The latent factors of users and items can be learned in these graph structure data. There are many methods for learning the latent factors of users and items. Still, they do not fully consider the influence of node attribute information on the representation of the latent factors of users and items. We propose a rating prediction recommendation model, short for LNNSR, utilizing the level of information granularity allocated on each attribute by developing a granular neural network. The different granularity distribution proportion weights of each attribute can be learned in the granular neural network. The learned granularity allocation proportion weights are integrated into the latent factor representation of users and items. Thus, we can capture user-embedding representations and item-embedding representations more accurately, and it can also provide a reasonable explanation for the recommendation results. Finally, we concatenate the user latent factor-embedding and the item latent factor-embedding and then feed it into a multi-layer perceptron for rating prediction. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jiangmei Chen ◽  
Wende Zhang ◽  
Qishan Zhang

PurposeThe purpose of the paper is to improve the rating prediction accuracy in recommender systems (RSs) by metric learning (ML) method. The similarity metric of user and item is calculated with gray relational analysis.Design/methodology/approachFirst, the potential features of users and items are captured by exploiting ML, such that the rating prediction can be performed. In metric space, the user and item positions can be learned by training their embedding vectors. Second, instead of the traditional distance measurements, the gray relational analysis is employed in the evaluation of the position similarity between user and item, because the latter can reduce the impact of data sparsity and further explore the rating data correlation. On the basis of the above improvements, a new rating prediction algorithm is proposed. Experiments are implemented to validate the effectiveness of the algorithm.FindingsThe novel algorithm is evaluated by the extensive experiments on two real-world datasets. Experimental results demonstrate that the proposed model achieves remarkable performance on the rating prediction task.Practical implicationsThe rating prediction algorithm is adopted to predict the users' preference, and then, it provides personalized recommendations for users. In fact, this method can expand to the field of classification and provide potentials for this domain.Originality/valueThe algorithm can uncover the finer grained preference by ML. Furthermore, the similarity can be measured using gray relational analysis, which can mitigate the limitation of data sparsity.


2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Tongyan Li ◽  
Yingxiang Li ◽  
Chen Yi-Ping Phoebe

Current data has the characteristics of complexity and low information density, which can be called the information sparse data. However, a large amount of data makes it difficult to analyse sparse data with traditional collaborative filtering recommendation algorithms, which may lead to low accuracy. Meanwhile, the complexity of data means that the recommended environment is affected by multiple dimensional factors. In order to solve these problems efficiently, our paper proposes a multidimensional collaborative filtering algorithm based on improved item rating prediction. The algorithm considers a variety of factors that affect user ratings; then, it uses the penalty to account for users’ popularity to calculate the degree of similarity between users and cross-iterative bi-clustering for the user scoring matrix to take into account changes in user’s preferences and improves on the traditional item rating prediction algorithm, which considers user ratings according to multidimensional factors. In this algorithm, the introduction of systematic error factors based on statistical learning improves the accuracy of rating prediction, and the multidimensional method can solve data sparsity problems, enabling the strongest relevant dimension influencing factors with association rules to be found. The experiment results show that the proposed algorithm has the advantages of smaller recommendation error and higher recommendation accuracy.


Author(s):  
Yingjie Liu ◽  
Xueyang Liu ◽  
Wenhui Hu ◽  
Minghui Zhang ◽  
Dongdong Du ◽  
...  

2021 ◽  
Vol 8 (9) ◽  
pp. 436-441
Author(s):  
Abdul Khaliq ◽  
Eko Hariyanto ◽  
Supina Batubara

Application developers and users are the keys to the market impact on application development. In application development, developers need to predict applications in the market accurately, accurate prediction results are very important in showing user ratings that affect the success of an application. Ratings are given by users to judge that the application is good or not. The higher the rating given by the user, it means that the user likes the application and can be a benchmark for other users to download the application. It is undeniable that there are so many apps available on the google play store, it is impossible for users to select one by one app on the google play store. Therefore, a rating prediction system is needed to determine the right application based on the rating given by the user to an application. Predictions will be made using the random forest algorithm as the method used to predict application ratings. This study using the Google Play Store dataset. This dataset has 10840 rows and 13 attributes. The results of this study can be seen from the use of the random forest algorithm with an average accuracy of 93.8%. Keywords: Google Play Store, Rating, Prediction, Random Forest.


Sign in / Sign up

Export Citation Format

Share Document