Proceedings of ELM-2016 pp 89-97 | Cite as
Hot News Click Rate Prediction Based on Extreme Learning Machine and Grey Verhulst Model
Abstract
Click rate prediction of hot topics contributes to get event tendency, especially for sensitive news. However, click rate prediction is challenge due to inherent features of short-time series such as randomness, uncertainty, volatility and insufficiency of training samples. In this paper, a new hybrid click rate prediction method called Grey Verhulst—Extreme Learning Machine (GVELM) is proposed. Specifically, the raw short-time series data are filled into GV models to acquire stably initial prediction which have incorporated regular pattern of the historic data without noise. Then ELM is employed for prediction refinement for nonlinear space mapping. The experimental results show that the proposed method achieves better prediction accuracy compared with other five state-of-art algorithms.
Keywords
Short-term time series prediction Extreme learning machine (ELM) Grey verhulst model (GV) GVELM modelNotes
Acknowledgements
This work was supported by NSFc 61202184, 61305032 and Scientific research plan projects 2015JQ6240.
References
- 1.Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70, 489–501 (2006)CrossRefGoogle Scholar
- 2.Deng, J.L.: Control problems of grey systems [J]. Syst. Control Lett. 1(5), 288–294 (1982)MathSciNetCrossRefMATHGoogle Scholar
- 3.Lee, Y.S., Tong, L.I.: Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming [J]. Knowl.-Based Syst. 24(1), 66–72 (2011)MathSciNetCrossRefGoogle Scholar
- 4.Wang, X., Qi, L., Chen, C., et al.: Grey system theory based prediction for topic trend on internet [J]. Eng. Appl. Artif. Intell. 29(3), 191–200 (2014)CrossRefGoogle Scholar
- 5.Liu, Y.K., Xie, F., Xie, C.L., et al.: Prediction of time series of NPP operating parameters using dynamic model based on BP neural network [J]. Ann. Nucl. Energ. 85, 566–575 (2015)CrossRefGoogle Scholar
- 6.Chandra, R.: Competition and collaboration in cooperative coevolution of elman recurrent neural networks for time-series prediction [J]. IEEE Trans. Neural Netw. Learn. Syst. 26(12), 1 (2015)MathSciNetCrossRefGoogle Scholar
- 7.Men, Z., Yee, E., Lien, F.S., Wen, D., Chen, Y.: Short-term wind speed and power forecasting using an ensemble of mixture density neural networks. Renew. Energ. 87, 203–211 (2016)CrossRefGoogle Scholar
- 8.Rubio, G., Pomares, H., Rojas, I., et al.: A heuristic method for parameter selection in LS-SVM: application to time series prediction [J]. Int. J. Forecast. 27(3), 725–739 (2011)CrossRefGoogle Scholar
- 9.Huang, G.B.: An insight into extreme learning machines: random neurons, random features and kernels [J]. Cogn. Comput. 6(3), 376–390 (2014)CrossRefGoogle Scholar
- 10.Liang, N.Y., Huang, G.B., Saratchandran, P., et al.: A fast and accurate online sequential learning algorithm for feedforward networks [J]. IEEE Trans. Neural Netw. 17(6), 1411–1423 (2006)CrossRefGoogle Scholar
- 11.Gardner, E.S.: Exponential smoothing: the state of the art [J]. J. Forecast. 4(1), 1–28 (1985)CrossRefGoogle Scholar
- 12.Zhou, D.: A new hybrid grey neural network based on grey verhulst model and BP neural network for time series forecasting [J]. Int. J. Inf. Technol. Comput. Sci. 5(10), 114–120 (2013)Google Scholar
- 13.Zhao, W., Wang, F., Niu, D.: The application of support vector machine in load forecasting [J]. J. Comput. 7(7) (2012)Google Scholar