Open Access

ARTICLE

A Novel Service Recommendation Approach in Mashup Creation

Yanmei Zhang¹, Xiao Geng², Shuiguang Deng³

1 Information School, Central University of Finance and Economics Beijing 100081, China
2 School of Computer Science, Wuhan University, Wuhan 430072 China
3 College of Computer Science and Technology Zhejiang University, Hangzhou 310027, China

* Corresponding Author: Yanmei Zhang,

Intelligent Automation & Soft Computing 2019, 25(3), 513-525. https://doi.org/10.31209/2019.100000108

Abstract

With the development of service computing technologies, the online services are massive and disordered now. How to find appropriate services quickly and build a more powerful composed service according to user interests has been a research focus in recent years. Current service recommendation algorithms often directly follow the traditional recommendation framework of ecommerce, which cannot effectively assist users to complete dynamic online business construction. Therefore, a novel service recommendation approach named UISCS (User-Interest- initial Services-Correlation-successor Services) is proposed, which is designed for interactive scenario of service composition, and it mines the user implicit interests and the service correlations for service recommendation. A series of experiments are conducted on a real-world dataset crawled from the ProgrammableWeb, and the results show that as a step-by-step service recommendation approach, the UISCS approach has obviously improved the performance of some mainstream recommendation algorithms, such as LDA, ICF , SVD and graph-based TSR.

---

Keywords

---