Effective learning model of user classification based on ensemble learning algorithms
- 49 Downloads
Aiming to aid Electric-Power Industry to accurately understand users, hybrid learning model based ensemble learning algorithms for recognizing user to be sensitive to electric charge is proposed in this paper. On the basis of big data presented by CCF competition sponsor in China, with some excellent technology or algorithm such as JieBa, SFFS, etc., we extract many key features from data set and successfully draw a portrait for users who pay close attention to electric charge. Furthermore, machine learning algorithms and the strategy selection model related to them are investigated. The feasibility that hybrid learning model combining several ensemble learning algorithms can substantially improve classification accuracy are proved from theoretical level. Then the details of implementing hybrid learning model are described in the paper. Lastly, the hybrid learning model named Stacking is achieved, which yields better performance in contrast to the state-of-the-art competitors. The experimental results indicate that Stacking has both high precision and recall with 0.8 and 0.85 respectively. Furthermore the F1 score of Stacking evaluation is 0.823.
KeywordsUser classification User portrait Machine learning algorithms Hybrid learning model
Mathematics Subject Classification68U04
This work has partly been supported by the Key project of national key R&D project (No. 2017YFC17003303), National Nature Science Foundation of China (Nos. 61402387), Science and Technology Guiding Project of Fujian Province of China (Nos. 2015H0037, 2016H0035), the Natural Science Foundation of Fujian Province, China (Grant Nos. 2017J01773, 2018J01555), the Educational Middle and Youth Foundation of Fujian Province, China (Grant No. JAT160537), the research program of normal university (Grant Nos. 2016Z06, 2016Z03), The authors would like to appreciate the valuable comments and suggestions from the editors and reviewers.
- 1.Zhao SG (2014) High conversions ratio user portrait of social media: deep investigation and research based 500 users. Mod Med J Commun Univ China 31:115–120Google Scholar
- 2.Customer portrait created by China grid client service central based on Big Data. http://www.chinapower.com.cn/dwzhxw/20160504/23472.html[DB/OL]. Accessed 07 Oct 2017
- 6.Rory M, Eibe F (2017) Accelerating the XGBoost algorithm using GPU computing. Peer J 5:341–345Google Scholar
- 7.Qiao Y, Zhang HP, Yu M. Sina-Weibo (2016) Spammer detection with GBDT, social media processing. In: 5th National conference on social media processing, 29–30 Oct, Nanchang, ChinaGoogle Scholar
- 8.Zhang XS, Zhuang Y, Wang W (2016) Transfer boosting with synthetic instances for class imbalanced object recognition. IEEE Trans Cybern 99:1–14Google Scholar
- 14.Hyoseon J, Woongwoo L, Hyeyoung P (2017) Automatic classification of tremor severity in Parkinson’s disease using a wearable device. Sensors 17:3390Google Scholar
- 17.Han H, Wang WY, Mao BH (2014) Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: 18th International conference on advances in intelligent computing, 5–7 May, Tokyo, JapanGoogle Scholar
- 19.Davila FC, Renatao DM (2016) A bee-inspired data clustering approach to design RBF neural network classifiers. Neurocomputing 79:852–863Google Scholar