计算机应用 ›› 2012, Vol. 32 ›› Issue (12): 3558-3560.DOI: 10.3724/SP.J.1087.2012.03558

• 典型应用 • 上一篇    下一篇

基于Adaboost算法和BP神经网络的税收预测

李翔,朱全银   

  1. 淮阴工学院 计算机工程学院,江苏 淮安 223003
  • 收稿日期:2012-07-25 修回日期:2012-08-18 发布日期:2012-12-29 出版日期:2012-12-01
  • 通讯作者: 李翔
  • 作者简介:李翔(1980-),男,江苏淮安人,讲师,硕士,CCF会员,主要研究方向:模式识别、人工神经网络;〓朱全银(1966-),男,江苏淮安人,教授,主要研究方向:人工神经网络。
  • 基金资助:
    国家星火计划;淮安市科技支撑计划项目

Tax forecasting based on Adaboost algorithm and BP neural network

LI Xiang,ZHU Quan-yin   

  1. Faculty of Computer Engineering, Huaiyin Institute of Technology, Huai’an Jiangsu 223003, China
  • Received:2012-07-25 Revised:2012-08-18 Online:2012-12-29 Published:2012-12-01
  • Contact: LI Xiang
  • Supported by:
    National Spark Program;The Technology Support Program of Huai'an

摘要: 针对传统税收预测模型精度较低的问题,提出一种将Adaboost算法和BP神经网络相结合进行税收预测的方法。该方法首先对历年税收数据进行预处理并初始化测试数据分布权值;然后初始化BP神经网络权值和阈值,并将BP神经网络作为弱预测器对税收数据进行反复训练和调整权值;最后使用Adaboost算法将得到的多个BP神经网络弱预测器组成新的强预测器并进行预测。通过对我国1990—2010年税收数据进行仿真实验,结果表明该方法相比传统BP网络预测,平均误差相对值从0.50%减少到0.18%,有效地降低了单个BP陷入局部极小的影响,提高了网络预测精度。

关键词: 神经网络, Adaboost算法, 强预测器, 迭代算法, 税收预测

Abstract: In view of the lower accuracy of traditional tax forecasting models, the authors put forward a method of combining the Adaboost algorithm with BP neural network to forecast revenue. Firstly, the method performed the pretreatment for the historical tax data and initialized the distribution weights of test data; secondly, it initialized the weights and thresholds of BP neural network, and used BP neural network as a weak predictor to train the tax data repeatedly and adjust the weights; finally, it made more weak predictors of BP neural network to form new strong predictors by Adaboost algorithm and forecasted. The authors also carried out simulation experiment for the tax data of China from 1990 to 2010. The results show that this method has reduced the relative value of mean error from 0.50% to 0.18% compared to the traditional BP network, has effectively reduced the effect when single BP gets trapped in local minima, and has improved the prediction accuracy of network.

Key words: neural network, Adaboost algorithm, strong predictor, iterative algorithm, tax forecasting