Service recommendation driven by a matrix factorization model and time series forecasting

Ngaffo, Armielle Noulapeu; Ayeb, Walid El; Choukair, Zièd

doi:10.1007/s10489-021-02478-0

Cited by 8 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tang et al [19] used the network map to measure the network distance between service and users and identify the neighbors of users by considering the impact of the underlying network on the QoS of web services, and they introduced the above two factors into the matrix factorization as constraints for calculation. And Ngaffo et al [20] used a flexible matrix factorization technique and a QoS prediction of the future time interval using a time series forecasting approach based on an autoregressive integrated moving average (ARIMA) model. But the latent vectors themselves made by MF are not explanatory, so Chang et al [21] introduced graph theory into the matrix factorization model to strengthen the interpretability and accuracy; this approach divides the user-service graph into a certain number of subgraphs by dividing the maximum subgraph, and then applies both the subgraph and the user-service graph to the matrix factorization model to perform local and global analysis and prediction.…”

Section: Collaborative Filtering Methodsmentioning

confidence: 99%

Location-Aware Deep Interaction Forest for Web Service QoS Prediction

Zhu,

Ding,

Yang

2024

Applied Sciences

View full text Add to dashboard Cite

With the rapid development of the web service market, the number of web services shows explosive growth. QoS is an important factor in the recommendation scene; how to accurately recommend a high-quality service for users among the massive number of web services has become a tough problem. Previous methods usually acquired feature interaction information by network structures like DNN to improve the QoS prediction accuracy, but this generates unnecessary computations. Aiming at addressing the above problem, inspired by the multigrained scanning mechanism in a deep forest, we propose a location-aware deep interaction forest approach for web service QoS prediction (LDIF). This approach offers the following innovations: The model fuses the location similarity of users and services as a latent feature representation of them. In addition, we designed a scanning interaction structure (SIS), which obtains multiple local feature combinations from the interaction between user and service features, uses interactive computing to extract feature interaction information, and concatenates the feature interaction information with original features, which aims to enhance the dimension of the features. Equipped with these, we compose a layer-by-layer cascade by using SIS to fuse low- and high-order feature interaction information, and the early-stop mechanism controls the cascade depth to avoid unnecessary computation. The experiments demonstrate that our model outperforms eight other state-of-the-art methods on MAE and RMSE common metrics on real public datasets.

show abstract

Section: Collaborative Filtering Methodsmentioning

confidence: 99%

Location-Aware Deep Interaction Forest for Web Service QoS Prediction

Zhu,

Ding,

Yang

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The model-based CF algorithm uses all QoS values (global information) in the user-service matrix to construct a global model for QoS value prediction, which compensates for the above shortcomings [24]. For example, the method in Ref [25] performs both a QoS prediction of the current time interval using a flexible matrix factorization (MF) technique and a QoS prediction of the future time interval using a time series forecasting method based on an Auto Regressive Integrated Moving Average (ARIMA) model. Dynamic relationships are frequently encountered in service computing related applications.…”

Section: )mentioning

confidence: 99%

Uncertain Big QoS Data-Driven Efficient SaaS Decision-Making Method

Zhang,

Bai

2024

IEEE Access

View full text Add to dashboard Cite

Selecting the QoS-optimized software-as-a-service (SaaS) from a large number of services with the same functionality and different Quality of Service (QoS) is still a hot issue. Massive QoS feedback forms big QoS data, which exhibits ambiguity and randomness increasing the uncertainty of service selection. Starting from the characterization of big QoS data, the Uncertain Big QoS data-driven Efficient SaaS Decision Making Method (UBQoS_ESDM) is proposed. The method firstly utilizes cloud model to portray QoS in order to solve the problem of inaccurate description of uncertain big QoS data; then draws on the idea of Skyline query to establish uncertain service Skyline set, which reduces the search space and improves the efficiency of QoS-optimal SaaS selection; and draws on the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) to design two decision-making algorithms to evaluate alternative SaaSs, and to obtain the QoS-optimal SaaS that reflects user requirements. In addition, two types of backward QoS cloud generators are introduced to convert big QoS data to QoS cloud models, and the QoS cloud model adaptive adjustment mechanism is introduced too, which can adapt to the dynamic changes of QoS. Finally, theoretical proofs and experiments verify the superiority and efficiency of the method.

show abstract

“…The matrix factorization factor model is widely used. The matrix factor algorithm is used to extract hidden factors from the evaluation matrix of user objects, and these factors are used to describe users and entities, as well as users' estimated values of other entities [3]. Besides, Angadi et al discussed Naive Bayes model.…”

Section: Introductionmentioning

confidence: 99%

Tourist Attraction Recommendation Method Based on Megadata and Artificial Intelligence Algorithm

Yun¹,

Jiao

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

As China’s economy continues to grow of informational technology and mobile Internet industry, the online tourism industry has received more and more extensive attention and use. However, as an emerging industry, users often need to spend a lot of time to choose travel services that match their needs because of the complex amount of relevant information. Under such circumstances, this paper studied the recommendation method in travel platform. First, the big data is used to extract user data. Secondly, the current online travel business recommendation for users has the problem of low accuracy. The reason is that the services provided are still in traditional recommendation algorithm. In this paper, the Bayesian network is used to evaluate the user’s attribute preference and generate a data model, using effective methods in artificial intelligence algorithms to improve collaborative filtering algorithms and finally generate hybrid recommendation algorithms. Compared with the traditional recommendation method, the experimental results showed that the research can improve the recommendation accuracy of tourist attractions by 6.55%, increase the user’s satisfaction for the platform, and enhance the visit rate and retention rate of the tourist attraction recommendation platform.

show abstract

Service recommendation driven by a matrix factorization model and time series forecasting

Cited by 8 publications

References 33 publications

Location-Aware Deep Interaction Forest for Web Service QoS Prediction

Location-Aware Deep Interaction Forest for Web Service QoS Prediction

Uncertain Big QoS Data-Driven Efficient SaaS Decision-Making Method

Tourist Attraction Recommendation Method Based on Megadata and Artificial Intelligence Algorithm

Contact Info

Product

Resources

About