Article: Predicting service collaboration for users based on data variation patterns Journal: International Journal of Information Technology and Management (IJITM) 2020 Vol.19 No.4 pp.261 - 279 Abstract: Service collaboration allows the realisation of more complicated business logic by using existing services. Nowadays, users use lots of services in their daily work. For example, developers use a large number of services (e.g., Stack Overflow, Github, Blogger, etc.) to develop programs. Services are used continuously. Since most of the users' data is distributed in these different service providers, these data are separated from each other although they are correlated. If we coordinate different services based on these correlation data, we can provide users with seamless and effective support. This is very significant because it greatly increases users' productivity. However, due to the segregation of data, it is difficult to coordinate different services based on data correlation. To deal with this challenge, we propose a novel deep recurrent neural network (runs in a centralised service) to predict future services collaboration and their generated data. The network captures the correlation between different data and discovers patterns of data variation by using multiple hidden layers, which are beneficial to services collaboration prediction. Extensive experiments are conducted on the real world dataset. Experimental results show that our model significantly outperforms a few competitive baseline methods. Inderscience Publishers - linking academia, business and industry through research

Title: Predicting service collaboration for users based on data variation patterns

Authors: Jiaqiu Wang; Zhongjie Wang

Addresses: School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China ' School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

Abstract: Service collaboration allows the realisation of more complicated business logic by using existing services. Nowadays, users use lots of services in their daily work. For example, developers use a large number of services (e.g., Stack Overflow, Github, Blogger, etc.) to develop programs. Services are used continuously. Since most of the users' data is distributed in these different service providers, these data are separated from each other although they are correlated. If we coordinate different services based on these correlation data, we can provide users with seamless and effective support. This is very significant because it greatly increases users' productivity. However, due to the segregation of data, it is difficult to coordinate different services based on data correlation. To deal with this challenge, we propose a novel deep recurrent neural network (runs in a centralised service) to predict future services collaboration and their generated data. The network captures the correlation between different data and discovers patterns of data variation by using multiple hidden layers, which are beneficial to services collaboration prediction. Extensive experiments are conducted on the real world dataset. Experimental results show that our model significantly outperforms a few competitive baseline methods.

Keywords: service collaboration prediction; correlation data; data variation; deep recurrent neural network.

DOI: 10.1504/IJITM.2020.110237

International Journal of Information Technology and Management, 2020 Vol.19 No.4, pp.261 - 279

Received: 12 Jun 2018
Accepted: 26 Mar 2019
Published online: 12 Oct 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Predicting service collaboration for users based on data variation patterns

Keep up-to-date