Web API Recommendation with Features Ensemble and Learning-to-Rank

  • Hua Zhao
  • Jing Wang
  • Qimin Zhou
  • Xin Wang
  • Hao WuEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1120)


In recent years, various methods against service ecosystem have been proposed to address the requirements on recommendation of Web APIs. However, how to effectively combine trivial features of mashups and APIs to improve the recommendation effectiveness remains to be explored. Therefore, we propose a Web API recommendation method using features ensemble and learning-to-rank. Based on available usage data of mashups and Web APIs, textual features, nearest neighbor features, API-specific features, tag features of APIs are extracted to estimate the relevance between the mashup requirement and the candidates of APIs in a regression model, and then a learning-to-rank approach is used to optimize the model. Experimental results show our proposed method is superior to some state-of-the-art methods in the performance of recommendation.


Web API recommendation Features ensemble Learning-to-rank Top-N recommendation 



This work is supported by the National Natural Science Foundation of China (61562090, 61962061), partially supported by the Yunnan Provincial Foundation for Leaders of Disciplines in Science and Technology, the Program for Excellent Young Talents of Yunnan University, the Project of Innovative Research Team of Yunnan Province (2018HC019).


  1. 1.
    Tan, W., Fan, Y., Ghoneim, A., et al.: From the service-oriented architecture to the web API economy. IEEE Internet Comput. 20(4), 64–68 (2016)CrossRefGoogle Scholar
  2. 2.
    Zhao, H.B. Prashant, D.: Towards automated RESTful web service composition. In: 2009 IEEE International Conference on Web Services, pp. 189–196. IEEE, USA (2009)Google Scholar
  3. 3.
    Liu, X., Hui, Y., Sun, W., et al.: Towards service composition based on Mashup. In: 2007 IEEE Congress on Services, pp. 332–339. IEEE, USA (2007)Google Scholar
  4. 4.
    Cao, B., Liu, J., Tang, M., et al.: Mashup service recommendation based on user interest and social network. In: 2013 IEEE 20th International Conference on Services, pp. 99–106. IEEE, USA (2013)Google Scholar
  5. 5.
    Zhong, Y., Fan, Y., Tan, W., et al.: Web service recommendation with reconstructed profile from mashup descriptions. IEEE Trans. Autom. Sci. Eng. 15(2), 468–478 (2018)CrossRefGoogle Scholar
  6. 6.
    Li, C., Zhang, R., Huai, J., et al.: A novel approach for API recommendation in mashup development. In: 2014 IEEE International Conference on Web Services, pp. 289–296. IEEE, USA (2014)Google Scholar
  7. 7.
    Cao, B., Liu, X., Rahman, M., et al.: Integrated content and network-based service clustering and web APIs recommendation for mashup development. IEEE Trans. Serv. Comput. 99, 1 (2017)CrossRefGoogle Scholar
  8. 8.
    Bao, Q., Gatlin, P., Maskey, M., et al.: A fine-grained API link prediction approach supporting mashup recommendation. In: 2017 IEEE International Conference on Web Services (ICWS), pp. 220–228. IEEE Computer Society, Honolulu (2017)Google Scholar
  9. 9.
    Cao, B., Tang, M., Huang, X.: CSCF: a mashup service recommendation approach based on content similarity and collaborative filtering. Int. J. Grid Distrib. Comput. 7(2), 163–172 (2014)CrossRefGoogle Scholar
  10. 10.
    Jiang, Y., Liu, J., Tang, M., et al.: An effective web service recommendation method based on personalized collaborative filtering. In: IEEE International Conference on Web Services, pp. 211–218. IEEE, Washington (2011)Google Scholar
  11. 11.
    Zheng, Z., Ma, H., Lyu, M.R., et al.: QoS-aware web service recommendation by collaborative filtering. IEEE Trans. Serv. Comput. 4(2), 140–152 (2011)CrossRefGoogle Scholar
  12. 12.
    Yao, L., Wang, X., Sheng, Q.Z., et al.: Mashup recommendation by regularizing matrix factorization with API co-invocations. IEEE Trans. Serv. Comput. 99, 1 (2018)CrossRefGoogle Scholar
  13. 13.
    Lo, W., Yin, J., Deng, S., et al.: collaborative web service Qos prediction with location-based regularization. In: 2012 IEEE 19th International Conference on Web Services, pp. 464–471. IEEE Computer Society, Honolulu (2012)Google Scholar
  14. 14.
    Rahman, M.M., Liu, X., Cao, B.: web API recommendation for mashup development using matrix factorization on integrated content and network-based service clustering. In: 2017 IEEE International Conference on Services Computing (SCC), pp. 225–232. IEEE Computer Society, Honolulu (2017)Google Scholar
  15. 15.
    Xia, B., Fan, Y., Tan, W., et al.: Category-aware API clustering and distributed recommendation for automatic mashup creation. IEEE Trans. Serv. Comput. 8(5), 674–687 (2017)CrossRefGoogle Scholar
  16. 16.
    Gao, W., Chen, L., Wu, J., et al.: Joint modeling users, services, mashups, and topics for service recommendation. In: 2016 IEEE International Conference on Web Services (ICWS), pp. 260–267. IEEE, San Francisco (2016)Google Scholar
  17. 17.
    Li, H., Liu, J., Cao, B., et al.: Integrating tag, topic, co-occurrence, and popularity to recommend web APIs for mashup creation. In: IEEE International Conference on Services Computing (SCC), pp. 84–91. IEEE, Honolulu (2017)Google Scholar
  18. 18.
    Wang, X., Wu, H., Hsu, C.H.: Mashup-oriented API recommendation via random walk on knowledge graph. IEEE Access 7, 7651–7662 (2019)CrossRefGoogle Scholar
  19. 19.
    Li, H.: A short introduction to learning to rank. IEICE Trans. Inf. Syst. E94–D(10), 1854–1862 (2011)CrossRefGoogle Scholar
  20. 20.
    Wu, H., Yue, K., Li, B., et al.: Collaborative QoS prediction with context-sensitive matrix factorization. Future Gener. Comput. Syst. 82, 669–678 (2018)CrossRefGoogle Scholar
  21. 21.
    Huang, K., Fan, Y., Tan, W.: An empirical study of programmable web: a network analysis on a service-mashup system. In: 2012 IEEE 19th International Conference on Web Services (ICWS), pp. 552–559. IEEE, Honolulu (2012)Google Scholar
  22. 22.
    Wu, H., Pei, Y., Li, B., Kang, Z., Liu, X., Li, H.: Item recommendation in collaborative tagging systems via heuristic data fusion. Knowl.-Based Syst. 75(1), 124–140 (2015)CrossRefGoogle Scholar
  23. 23.
    Hoffman, M.D., Blei, D.M., Bach, F.R.: Online learning for latent dirichlet allocation. In: Advances in Neural Information Processing Systems, vol. 23, pp. 856–864. Natural and Synthetic, Canada (2010)Google Scholar
  24. 24.
    Robertson, S.E., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends® Inf. Retr. 3(4), 333–389 (2009)CrossRefGoogle Scholar
  25. 25.
    Ketkar, N.: Stochastic gradient descent. In: Deep Learning with Python, pp. 113–132. Apress, Berkeley (2017)Google Scholar
  26. 26.
    Dojchinovski, M., Vitvar, T., Hoekstra, R.: Linked web apis dataset. Seman. Web 9(3), 1–11 (2017)Google Scholar
  27. 27.
    Rosen-Zvi, M., Griffiths, T., Steyvers, M., et al.: The author-topic model for authors and documents. In: Proceedings of the 20th Conference in Uncertainty in Artificial Intelligence, pp. 487–494. DBLP, Canada (2004)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.School of Information Science and EngineeringYunnan UniversityKunmingChina
  2. 2.National Pilot School of SoftwareYunnan UniversityKunmingChina

Personalised recommendations