%0 Journal Article
%T 基于Keras的LSTM网络在死亡率预测的应用<br>Application of LSTM Networks Based on Keras in Mortality Prediction
%A 肖鸿民
%A 李祥
%J Advances in Applied Mathematics
%P 3477-3486
%@ 2324-8009
%D 2021
%I Hans Publishing
%R 10.12677/AAM.2021.1010367
%X 随着人口老龄化程度进一步加深，加之人口死亡率的持续下降和人口预期寿命的不断延长，对死亡率有更加有效的预测，在长寿风险的研究中尤为重要。在以往的死亡率预测中，死亡率模型的时间项大多采用传统的ARIMA时间序列方法进行预测。本文选取中国人口死亡率数据，以长短期记忆(LSTM)网络和全连接层为基础，构建基于循环神经网络的LSTM学习机，用于预测Lee-Carter模型的时间项。<br />
As the aging degree of the population deepens, coupled with the continuous decline in population mortality and prolonged life expectancy, a more effective prediction of mortality is particularly important in the study of longevity risk. In previous mortality predictions, the time terms of mortality models were mostly predicted using traditional ARIMA time series methods. This paper selects Chinese population mortality data, based on long-short term memory (LSTM) network and dense layers, constructing a LSTM learning machine based on recurrent neural network to predict the time term of the Lee-Carter model.
%K 死亡率预测，循环神经网络，时间序列分析，LSTM<br>Mortality Prediction
%K Recurrent Neural Network
%K Analysis of Time Series
%K LSTM
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=46002