兰州大学机构库 >数学与统计学院
应用X-12-ARIMA与SARIMA模型及其组合模型对中国保费收入的预测研究
Alternative TitleUSE X-12-ARIMA AND SARIMA MODEL AND COMBINED MODEL PREDICTING CHINESE PREMIUM INCOME
冯超
Thesis Advisor牛明飞
2014-06-01
Degree Grantor兰州大学
Place of Conferral兰州
Degree Name硕士
KeywordX-12-ARIMA季节调整 SARIMA模型 保费收入 季节性 预测
Abstract随着近年我国经济的高速腾飞,国民收入的迅猛增长,居民对保险的依赖程度逐步加强,我国保费收入也呈现逐年增长的趋势[1]。因此,我们必要寻找科学的方法对保费收入进行准确的预测。由于保费收入具有明显的季节性特征[2],本文采用先定季节指数方法和X-12方法对保费收入进行分析,结果表明X-12方法更应用于此数据的季节性特征分析。为更好地预测保费收入的增长,本文首先建立季节性差分自回归滑动平均模型(SARIMA)和基于X-12乘法模型的自回归滑动平均模型(X-12-ARIMA乘法模型)以及基于X-12加法模型的自回归滑动平均模型(X-12-ARIMA加法模型)。通过此三个模型之间的比较,表明SARIMA模型和X-12-ARIMA乘法模型明显优于X-12-ARIMA加法模型。然后,本文提出SARIMA和X-12-ARIMA乘法模型相结合的组合模型对保费收入进行最终预测。在此组合模型中,我们采用粒子群优化算法对两模型的权重进行优化。最后我们对中国主要保险公司1999年1月至2013年6月间月度保费总收入时间序列[3]进行实证分析,并对我国保费收入变化趋势进行预测,从而为我国保险业以及国家对于保险业的监管提供必要的支持。
Other AbstractAlong with the swift development of economy and the rapid growth of the national income, there is a growing inhabitants’ demand for insurance, resulting in the increasing trend of the premium income also year by year. Therefore, it is very necessary to find the scientific method to accurately predict the premium income. Due to the obvious seasonal characteristic of the premium income series, this article employs the first seasonal index method and X - 12 method to capture this character of premium income, the results show that X - 12 method shows superiority over the first seasonal index method in analysis of the seasonal characteristics. To better predict the growth of premium income, this paper firstly establishes the seasonal difference auto-regressive moving average (SARIMA) model, and the X - 12 multiplication model --based auto-regressive moving average model (X - 12 - multiplication ARIMA model) and X-12 additive model-based auto-regressive moving average model (X - 12 - ARIMA model). Through the comparison between these models, it is found that SARIMA model and X - 12 - ARIMA multiplication model is superior to X - 12 - ARIMA additive model. Then, this paper combines SARIMA multiplication model and X - 12 - ARIMA model to the final prediction of the premium income. In this combinational model, the particle swarm optimization algorithm is used to optimize the weight of two models. Finally we make empirical analysis to the monthly premium income of the major insurance companies of China between January 1999 and June 1999, and predict the trend of the premium income in our country, thereby providing necessary support for the insurance industry and the regulation to insurance industry.
URL查看原文
Language中文
Document Type学位论文
Identifierhttps://ir.lzu.edu.cn/handle/262010/224394
Collection数学与统计学院
Recommended Citation
GB/T 7714
冯超. 应用X-12-ARIMA与SARIMA模型及其组合模型对中国保费收入的预测研究[D]. 兰州. 兰州大学,2014.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[冯超]'s Articles
Baidu academic
Similar articles in Baidu academic
[冯超]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[冯超]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.