{"title":"A data mining approach to forming general work breakdown structure","authors":"Shan Mi-yuan, She Xiaohua, Ren Bin","doi":"10.1109/ICSESS.2011.5982230","DOIUrl":null,"url":null,"abstract":"To meet the development trend of the multi-project operations, this paper describes the concepts of project family and general work breakdown structure (GWBS), and then presents a data mining approach to forming GWBS. Work breakdown structure (WBS) instances are represented by a tree graph, and then we propose a similarity metric between a pair of WBS trees. The results of the pairwise comparisons are used as a distance metric for the following k-medoids clustering algorithm that groups the project WBSs into project families. Each classified cluster represents a project family, and it is expressed by a GWBS. Since the GWBS comes from large amount of historical WBS data, its adaptability and configuration ability are improved effectively, and all of these provide a strong guarantee for enterprises to respond quickly to customer needs.","PeriodicalId":108533,"journal":{"name":"2011 IEEE 2nd International Conference on Software Engineering and Service Science","volume":"60 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 IEEE 2nd International Conference on Software Engineering and Service Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSESS.2011.5982230","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
To meet the development trend of the multi-project operations, this paper describes the concepts of project family and general work breakdown structure (GWBS), and then presents a data mining approach to forming GWBS. Work breakdown structure (WBS) instances are represented by a tree graph, and then we propose a similarity metric between a pair of WBS trees. The results of the pairwise comparisons are used as a distance metric for the following k-medoids clustering algorithm that groups the project WBSs into project families. Each classified cluster represents a project family, and it is expressed by a GWBS. Since the GWBS comes from large amount of historical WBS data, its adaptability and configuration ability are improved effectively, and all of these provide a strong guarantee for enterprises to respond quickly to customer needs.