基于ARIMA对养老床位数量的预测

Prediction of Time Series of Nursing Bed Number Based on ARIMA

随着人口总数的不断增加和人口老龄化的加剧,如何预测养老床位的需求以及应对随之而来的各种养老问题,对于个人、企业、政府都至关重要。因此,可依据各类信息、数据对养老床位的需求进行预测,并给出合理的建议与运营策略。本文综合选取了全国总人口、老年人比例、人口死亡率、卫生机构床位数、全国GDP、离退人员参加养老保险人数这六个元素作为影响因素,针对不同数据的特征,使用Brown线性趋势模型、时间序列分析模型对这些指标进行了十年的数据预测,再用ARIMA对养老床位需求规模进行预测,使用神经网络对结果进行修正,最终得到养老床位需求的分类预测结果。最后使用主成分分析法对各指标进行降维,将主成分归类为三大指标,提出了关于如何建设养老服务的建议。

With the continuous increase of the total population and the aggravation of the aging of the popu-lation, how to predict the demand for pension beds and deal with the ensuing various pension problems are of great importance to individuals, enterprises and the government. Therefore, the demand for old-age care beds can be predicted based on all kinds of information and data, and reasonable suggestions and operation strategies can be given. The paper selected the population proportion of the population, the elderly, mortality, and health institutions of beds, the national GDP, the number of personnel to attend endowment insurance applicant retreating the six ele-ments as influence factors, according to the characteristics of the different data, using Brown linear trend model, time series analysis model for data to predict these indexes for ten years. Then ARIMA was used to predict the demand scale of elderly care beds, and neural network was used to modify the results, finally the classification prediction results of elderly care bed demand were obtained. Finally, the principal component analysis method is used to reduce the dimension of each index, the principal component is classified into three indicators, and the suggestions on how to build old-age service are put forward.