Open APIs recommendation with an ensemble-based multi-feature model
作者：
Highlights：
• We propose an ensemble-based approach to Open APIs recommendation with a multiple feature model.
• We integrate GBDT and GRU to obtain the similarity between Open APIs and composite applications.
• We make a set of comparative experiments based on the real data set of the Programmable Web.
• Experimental results show the effectiveness of our approach on Open APIs recommendation.
• Our approach can be fully reused by software developers to develop Web-based applications.
摘要
•We propose an ensemble-based approach to Open APIs recommendation with a multiple feature model.•We integrate GBDT and GRU to obtain the similarity between Open APIs and composite applications.•We make a set of comparative experiments based on the real data set of the Programmable Web.•Experimental results show the effectiveness of our approach on Open APIs recommendation.•Our approach can be fully reused by software developers to develop Web-based applications.
论文关键词：Open APIs,APIs recommendation,Neural networks,Machine learning,Ensemble model
论文评审过程：Received 18 February 2021, Revised 15 November 2021, Accepted 17 January 2022, Available online 8 February 2022, Version of Record 17 February 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116574
