Analysis and Prediction Model of Financial Income in Guangzhou
Abstract: Local financial revenue is an important part of national fiscal revenues. In order to identify the impact affecting factors of Guangzhou’s fiscal revenue automatically, we established a variable se-lection model in Adaptive-Lasso based on 1994-2013 years’ economic data. Under the research above, the paper offered the predictive value of fiscal revenue from 2014 to 2015 based on grey prediction and BP neural network combined model. The results of the variable selection models showed that the social number of employees, the total of worker’s salary, total volume of retail sales of the social consumer goods, per capita disposable income in urban residents, per capita expenditure on consumption in urban residents and social fixed assets investment were more re-lated to fiscal revenue; afterwards the combined model had better effects. Furthermore, some ad-vices were presented.
文章引用: 陈庚 , 卢丹丹 , 万浩文 , 王国长 (2015) 广州市财政收入分析及预测模型。 统计学与应用， 4， 187-195. doi: 10.12677/SA.2015.43021
 尚元君, 瑞锋 (2009) 地方政府财政收入能力影响因素的实证分析. 中央财经大学学报, 5, 12-15.
 刘心竹, 李昊, 等 (2012) 我国地方财政收入影响因素的实证分析. 中国集体经济, 9, 84-85.
 成军 (2003) 地方财政收入预测模型设计及实证分析. 经济研究参考, 88, 27-34.
 何邓娇 (2014) 广州市财政收入影响因素的实证研究. 经济研究导刊, 15, 104-106.
 Tibshirani, R. (1996) Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B, 58, 267-288.
Zou, H. (2006) The adaptive lasso and its oracle properties. Journal of the American Statistical Association, 101, 1418- 1429.
Fan, J.Q., Feng, Y. and Wu, Y.C. (2009) Network exploration via the adaptive lasso and SCAD penalties. The Annals of Applied Statistics, 3, 521-541.
Rumelhart, D.E., Hinton, G.E. and Williams, R.J. (1986) Learning re-presentations by back-propagating errors. Nature, 323, 533-536.
 史峰, 王辉, 等 (2011) MATLAB智能算法30个案例分析. 北京航空航天大学出版社, 北京.
 陈共 (2012) 财政学. 中国人民大学出版社, 北京.