Research on Premium Income Prediction Based on LSTM Neural Network

Main Article Content

Li Diao
Ning Wang


As one of the four financial pillars, insurance has the functions of risk diversification, loss compensation, financing and social management. It is of great practical significance to predict the level of premium income in the new normal of economy. In this paper, long short-term memory (LSTM) neural network was innovatively applied to the study of premium income prediction. The monthly data of China's premium income from January 1999 to October 2019 was selected for prediction, and the prediction results were compared with BP neural network. The results show that LSTM model can accurately predict premium income, and its performance is better than BP neural network.

Article Details

How to Cite
Diao, L., & Wang, N. (2019). Research on Premium Income Prediction Based on LSTM Neural Network. Advances in Social Sciences Research Journal, 6(11), 256-260.


[1] Duan Y J, Lv Y S, Wang F Y. Travel time prediction with LSTM neural network[C]// 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 2016.
[2] YANG H M, PAN Z S, BAI W. Review of Time Series Prediction Methods[J]. Computer Science, 2019, 46(01):28-35.
[3] WANG J T. Financial Time Series Prediction Based on LSTM Hybrid Model [D]. Zhengzhou: Zhengzhou University,2019.
[4] HOCHREITER S, SCHMIDHUBER J. Long Short-Term Memory[J]. Neural Computation,1997, 9(8):1735-1780.
[5] Graves A, Liwicki M, Santiago Fernández, et al. A Novel Connectionist System for Unconstrained Handwriting Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(5):855-868.
[6] GRAVES A, JAITLY N, MOHAMED A R. Hybrid speech recognition with Deep Bidirectional LSTM[C]// Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. IEEE, 2013.
[7] GRAVES A, SCHMIDHUBER J. Offline Arabic Handwriting Recognition with Multidimensional Recurrent Neural Networks[C]// Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008.