基于X12-LSTM模型的保费收入预测研究

doi:10.11896/JsJkx.191100077

计算机科学 ›› 2020, Vol. 47 ›› Issue (6A): 512-516.doi: 10.11896/JsJkx.191100077

• 数据库 & 大数据 & 数据科学 • 上一篇下一篇

基于X12-LSTM模型的保费收入预测研究

刁莉¹, 王宁²

1 中央财经大学保险学院北京 100081;
2 北京交通大学计算机与信息技术学院北京 100044

发布日期:2020-07-07
通讯作者: 刁莉(diaolibJwz@163.com)

Research on Premium Income Forecast Based on X12-LSTM Model

DIAO Li¹ and WANG Ning²

1 School of Insurance,Central University of Finance and Economics,BeiJing 100081,China
2 School of Computer and Information Technology,BeiJing Jiaotong University,BeiJing 100044,China

Published:2020-07-07
About author:GRAVES A, JAITLYN, MOHAMED A R.Hybrid speech re-cognition with Deep Bidirectional LSTM//2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).IEEE, 2013.
DIAO Li, born in 1992, Ph.D. Her main research interests include riskmanagement andinsurance.

摘要/Abstract

摘要： 经济新常态下保费收入预测是学术界和业界共同关注的话题。考虑到保费收入时间序列数据具有强烈的季节性特点,文中构建基于长短期记忆(Long Short-Term Memory,LSTM)神经网络的X12-LSTM模型以预测保费收入,并与简单LSTM模型、SARIMA模型和BP神经网络进行对比。实验结果表明,X12-LSTM模型对保费收入的预测最准确且稳定度最好。相比简单LSTM模型,X12-LSTM模型在准确度方面提升8%,在稳定度方面提升8%,说明X12-LSTM模型是对简单LSTM模型的有效改进,更适用于具有季节性特征的数据预测。

关键词: SARIMA, X12季节调整法, 保费收入预测, 长短期记忆神经网络, 季节性

Abstract: Under the new normal of economy,the prediction of premium income is a topic of common concern in academia and industry.Considering the strong seasonality of the time series data of premium income,an X12-LSTM model based on long short-term memory neural network is constructed to predict premium income,and compared with simple LSTM model,SARIMA model and BP neural network in this paper.Experimental results show that X12-LSTM model is the most accurate and stable model to predict premium income.Compared with simple LSTM model,the X12-LSTM model achieves an improvement of 8% in accuracy and 8% in stability,which shows that X12-lstm model is an effective improvement on simple LSTM model and is more suitable for data prediction with seasonality.

Key words: Long Short-Term Memoryneural networks, Premium Forecast, SARIMA, Seasonality, X12 seasonal adJustment

中图分类号:

TP391

刁莉, 王宁. 基于X12-LSTM模型的保费收入预测研究[J]. 计算机科学, 2020, 47(6A): 512-516. https://doi.org/10.11896/JsJkx.191100077

DIAO Li and WANG Ning. Research on Premium Income Forecast Based on X12-LSTM Model[J]. Computer Science, 2020, 47(6A): 512-516. https://doi.org/10.11896/JsJkx.191100077

参考文献

[1] BURCAAM,BATRINCAG.Application of Autoregressive Models for Forecasting Marine Insurance Market//Ovidius University Annals,Economic Sciences Series.2013.
[2] FUY H.An Application of ARIMA Model to the Prediction of the Property Insurance Premiums in China.Statistical Education,2010(10):54-57.
[3] SUN J Y,TIAN L N,LI B Q,et al.Time Series Forecasting of Chinese Insurance Corporation Premium Income.Journal of Gansu Sciences,2011,23(4):143-147.
[4] HE X,ZHANG H M.The Trend Analysis of Life Insurance Premium Income Time Series Based on SARIMA Model in Underdeveloped Areas－A Case Study of Guizhou Province//International Seminar on Education Innovation and Economic Management.2017.
[5] LIU Y H.Breakpoint Analysis of Life Insurance Premium Time Series Based on SARIMA Model.Collected Essays on Finance and Economics,2013(2):73-81.
[6] WIKTOR O.Time Series Forecasting of the Development of the Insurance Industry in Poland//Humboldt-Universitt zu Berlin,Wirtschaftswissenschaftliche Fakultt.2013.
[7] TIAN X Y.The Influential Factors Analysis and the Time Series Analysis of the Chinese Insurance Indusry Development .BeiJing:BeiJing Univerity of Technology,2017.
[8] ZHANG J L.Premium Proportion Prediction of China Insurance Based on GM(1,1).Technoeconomics & Management Research,2010(1):121-124.
[9] HAN W Q.The application of grey prediction model in the insurance premium prediction of Shandong Province .Journal of Insurance Vocational College,2017(1):37-39.
[10] YANG H M,PAN Z S,BAI W.Review of Time Series Prediction Methods.Computer Science,2019,46(1):28-35.
[11] WANG J T.Financial Time Series Prediction Based on LSTM Hybrid Model .Zhengzhou:Zhengzhou University,2019.
[12] SONG Y H,HU L J.Research on the prediction method of local economic GDP .Economic Research Guide,2017(32):4-9.
[13] HOCHREITER S,SCHMIDHUBER J.Long Short-Term Memory.Neural Computation,1997,9(8):1735-1780.
[14] GRAVES A,SCHMIDHUBER J.Offline Arabic Handwriting Recognition with Multidimensional Recurrent Neural Networks//Advances in Neural Information Processing Systems 21,Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems,Vancouver,British Columbia,Canada,2008:8-11.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于X12-LSTM模型的保费收入预测研究

Research on Premium Income Forecast Based on X12-LSTM Model

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	魏辉, 陈泽茂, 张立强. 一种基于顺序和频率模式的系统调用轨迹异常检测框架 Anomaly Detection Framework of System Call Trace Based on Sequence and Frequency Patterns 计算机科学, 2022, 49(6): 350-355. https://doi.org/10.11896/jsjkx.210500031
[2]	刘梦炀, 武利娟, 梁慧, 段旭磊, 刘尚卿, 高一波. 一种高精度LSTM-FC大气污染物浓度预测模型 A Kind of High-precision LSTM-FC Atmospheric Contaminant Concentrations Forecasting Model 计算机科学, 2021, 48(6A): 184-189. https://doi.org/10.11896/jsjkx.200600090
[3]	包振山, 郭俊南, 谢源, 张文博. 基于LSTM-GA的股票价格涨跌预测模型 Model for Stock Price Trend Prediction Based on LSTM and GA 计算机科学, 2020, 47(6A): 467-473. https://doi.org/10.11896/JsJkx.190900128
[4]	余珊珊, 苏锦钿, 李鹏飞. 一种基于自注意力的句子情感分类方法 Sentiment Classification Method for Sentences via Self-attention 计算机科学, 2020, 47(4): 204-210. https://doi.org/10.11896/jsjkx.190100097
[5]	杨佳宁, 黄向生, 李宗翰, 荣灿, 刘道伟. 基于双层栈式长短期记忆的电网时空轨迹预测 Spatio-temporal Trajectory Prediction of Power Grid Based on Double Layers Stacked Long Short-term Memory 计算机科学, 2019, 46(11A): 23-27.