计算机科学 ›› 2018, Vol. 45 ›› Issue (1): 179-182.doi: 10.11896/j.issn.1002-137X.2018.01.031
费鹏,林鸿飞,杨亮,徐博,古丽孜热·艾尼外
FEI Peng, LIN Hong-fei, YANG Liang, XU Bo and Gulziya ANIWAR
摘要： 电网公司的电费敏感客户往往对由用电引发的电量、电价、电费、缴费、欠费等电力服务具有强烈反应。快速定位电费敏感客户,对降低客户投诉率、提升客户满意度、树立供电企业良好的服务形象具有重要的作用。基于电网用户数据,提出了一种用于构建用户画像的多视角融合框架,该框架能够快速、准确地识别出电费敏感客户。首先,对电网用户进行了分析研究,利用双通道对不同特性的用户分别建模预测；其次,提出了多种特征萃取方法,用于构建用户多源特征体系；最后,为了充分利用多源特征,进一步提出了基于双层Xgboost的多视角融合模型。该框架在2016CCF大数据与计算智能大赛“客户画像”竞赛中获得了F1值为0.90379(第一名)的成绩,其有效性得到了验证。
| [1] ROSENTHAL S,MCKEOWN K.Age Prediction in Blogs:AStudy of Style,Content,and Online Behavior in Pre-and Post-Social Media Generations[C]∥The 49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies.Portland,Oregon,USA,2011:763-772. [2] MUELLER J,STUMME G.Gender Inference using Statistical Name Characteristics in Twitter.https:/arxiv.org/pdf/1606.05467v2.pdf. [3] MARQUARDT J,FARNADI G,VASUDEVAN G,et al.Age and Gender Identification in Social Media[C]∥Proceedings of CLEF 2014 Evaluation Labs.2014:1129-1136. [4] WU L,GE Y,LIU Q,et al.Modeling users’ preferences and social links in Social Networking Services:a joint-evolving perspective[C]∥Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence.2016:279-286. [5] MA H,CAO H,YANG Q,et al.A habit mining approach for discovering similar mobile users[C]∥Proceedings of the 21st International Conference on World Wide Web.ACM,2012:231-240. [6] ZHU H,CHEN E,XIONG H,et al.Mining mobile user prefe-rences for personalized context-aware recommendation[J].ACM Transactions on Intelligent Systems and Technology,2015,5(4):1-27. [7] ZHANG K.Mobile Phone User Profile in Large Data Platform[J].Information and Communications,2014(2):266-267.(in Chinese) 张慷.手机用户画像在大数据平台的实现方案[J].信息通信,2014(2):266-267. [8] HUANG W B,XU S C,WU J H,et al.The Profile Constructionof the Mobile User[J].Journal of Modern Information,2016,36(10):54-61.(in Chinese) 黄文彬,徐山川,吴家辉,等.移动用户画像构建研究[J].现代情报,2016,36(10):54-61. [9] MA L,TAO L T,XIE J K.Customer demands managementbased on tho customer portraits[J].Power Demand Side Mana-gement,2016(A01):98-100.(in Chinese) 马亮,陶利涛,谢骏凯.基于客户画像的客户诉求管理[J].电力需求侧管理,2016 (A01):98-100. [10] YAN Y P,WU G C.Customer Outage Sensitivity based on the Technology of Data Mining Research and Application[J].New Technology and New Process,2015(9):89-93.(in Chinese) 严宇平,吴广财.基于数据挖掘技术的客户停电敏感度研究与应用[J].新技术新工艺,2015(9):89-93. [11] CHEN T,GUESTRIN C.Xgboost:A scalable tree boosting system[C]∥Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2016:785-794. [12] DIERCKX,GOEDELE.Logistic Regression Model[J].Encyclopedia of Actuarial Science,2009,39(2):261-291. [13] HEARST M A,DUMAIS S T,OSMAN E,et al.Support vector machines[J].IEEE Intelligent Systems,1998,13(4):18-28. [14] QUINLAN J R.C4.5:programs for machine learning[M].Elsevier,2014. [15] BREIMAN L.Random forests[J].Machine learning,2001,45(1):5-32. [16] FRIEDMAN J H.Greedy Function Approximation:A Gradient Boosting Machine[J].Annals of Statistics,2000,29(5):1189-1232. [17] BREIMAN L.Stacked regressions[J].Machine Learning,1996,24(1):49-64. [18] BREIMAN L.Bagging predictors[J].Machine Learning,1996,24(2):123-140. |
| No related articles found! |
|
||
首页