基于LSTM循环神经网络的税收预测

doi:10.11896/jsjkx.200300091

摘要/Abstract

摘要： 分析历史税收数据之间的隐藏关系,利用数学模型来预测未来的税收收入是税收预测的研究重点。在此,提出了一种结合小波变换的长短期记忆(LSTM)循环神经网络的税收预测模型。在数据预处理上结合小波变换来去除税收数据中的噪声,提高模型的泛化能力。LSTM神经网络通过加入隐藏神经单元和门控单元能够更好地学习到历史税收数据之间的相关关系,并进一步提取有效的输入序列间的状态新息,而且解决了循环神经网络的长期依赖问题。实验结果表明,基于LSTM神经网络的编码器-解码器结构能够增强税收预测的时间步长,在中长期的税收预测中相比单步滑动窗口的LSTM神经网络模型以及基于差分微分方程的灰色模型和基于回归的自回归移动平均模型(ARIMA),在预测精度上有明显提升。

关键词: 编码器-解码器, 长短期记忆网络, 税收预测, 小波变换

Abstract: Analyzing the hidden relationship between historical tax data and using mathematical models to predict future tax revenue is the focus of tax forecast research.A tax prediction model of long short-term memory (LSTM) recurrent neural network combined with wavelet transform is proposed in this paper.Combining wavelet transform on data preprocessing to remove noise from tax data and improve the generalization ability of the model.The LSTM neural network can better learn the correlation between historical tax data by adding hidden neural units and gated units,and further extract valid state innovations between input sequences,and overcome the long-term dependency problem of recurrent neural networks.Experimental results show that the encoder-decoder structure based on the LSTM neural network can enhance the time step of tax prediction.Compared with the single-step sliding window LSTM neural network model and the gray model based on difference differential equations in the long-term tax prediction,the model and the regression-based autoregressive moving average model (ARIMA) significantly improve the prediction accuracy.

Key words: Encoder-decoder, Long-short term memory network, Tax forecasting, Wavelet transform

中图分类号:

TP183

文豪, 陈昊. 基于LSTM循环神经网络的税收预测[J]. 计算机科学, 2020, 47(11A): 437-443. https://doi.org/10.11896/jsjkx.200300091

WEN Hao, CHEN Hao. Tax Prediction Based on LSTM Recurrent Neural Network[J]. Computer Science, 2020, 47(11A): 437-443. https://doi.org/10.11896/jsjkx.200300091

参考文献

[1] WANG Y,LI Y,WANG L L,et al.Software stage effort prediction based on analogy and grey model [J].Computer Science,2018,45(S2):480-487.
[2] ZHAO Z,WANG J Z,ZHAO J,et al.Using a grey model optimized by differential evolution algorithm to forecast the per capita annual net income of rural households in China[J].Omega-International Journal of Management Science,2012,40(5):525-532.
[3] XIANG C S,ZHANG L F.Grain yield prediction model based on grey theory and markvo[J].Computer Science,2013,40(2):245-248.
[4] MALDONADO-MOLINA M M,WAGENAAR A C.Effects of Alcohol Taxes on Alcohol-Related Mortality in Florida:Time-Series Analyses From 1969 to 2004[J].Alcoholism-Clinical And Experimental Research,2010,34 (11):1915-1921.
[5] LIN J L.Application of time series model in customs revenue forecasting[J].Statistics and consulting,2008,2008(5):46-47.
[6] HAVIV D,RIVKIND A,BARAK O.Understanding and Controlling Memory in Recurrent Neural Networks[C]//Thirty-sixth International Conference on Machine Learning.2019:2663-2671.
[7] WANG Y Y,SMOLA A,MADDIX D C,et al.Deep Factors for Forecasting[C]//Thirty-sixth International Conference on Machine Learning.2019.
[8] CHARLES A,YIN D,ROZELL C.Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks[J].Journal of Machine Learning Research,2017,18(7):1-37.
[9] GERS F A,ECK D,SCHMIDHUBER J.Applying LSTM to time series predictable through time-window approach[C]//Proceedings of the 2001 International Conference on Artificial Neural Networks.London:Springer-Verlag,2001:669-676.
[10] SUTSKEVER I,VINYALS O,LE Q V.Sequence to sequence learning with neural networks[C]//Neural Information Processing Systems 2014.Advances in neural information processing systems,2014:3104-3112.
[11] SONG K T,TAN X,QIN T,et al.Tie-Yan Liu.MASS:Masked Sequence to Sequence Pre-training for Language Generation[C]//Thirty-sixth International Conference on Machine Learning.2019.
[12] TAY Y,PHAN M C,TUAN L A,et al.Learning to RankQuestion Answer Pairs with Holographic Dual LSTM Architecture[C]//The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval,2018.ACM,2018:325-324.
[13] GAO T W,CHAI Y T,LIU Y.Applying long short term me-mory neural networks for predicting stock closing price [C]//2017 8th IEEE International Conference on Software Engineering and Service Science.IEEE,2017:575-578.
[14] HE Z,GAO S B,XIAO L,et al.Wider and Deeper,Cheaper and Faster:Tensorized LSTMs for Sequence Learning [C]//Advances in Neural Information Processing Systems 30 (NIPS 2017).Curran Associates Inc,2017:1-11.
[15] JIA L,ZHENG C J.Short-term Forecasting Model of Agricultural Product Price Index Based on LSTM-DA Neural Network[J].Computer Science,2019,2019,46(S2):62-65,71.
[16] ESSIEN A,GIANNETTI C.A Deep Learning Framework forUnivariate Time Series Prediction Using Convolutional LSTM Stacked Autoencoders [C]//2019 IEEE International Symposiumon Innovations in Intelligent Systems and Applications.IEEE,2019:1-6.
[17] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[18] CHO K,BAHDANAU D,BOUGARES F,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].EMNLP,2014:1724-1734.
[19] POPOOLA A,AHMAD K.Testing the suitability of wavelet preprocessing for TSK fuzzy models[C]//ICFS 2006:2006 IEEE International Conference on Fuzzy Systems.IEEE,2006:1305-1309.
[20] ZHAO A,ZHANG D,SHI J Q.Forecasting and Analysis ofEUR/USD Exchange Rate Moving Direction with Support Vector Machine [C]//2018 IEEE 8th Annual International Conference on CYBER Technology in Automation,Control,and Intelligent Systems.IEEE,2018:1484-1489.
[21] ZHANG S X,CONG X R.The Application of Wavelet Analysis in Financial Multiple Change Points Time Series [C]//2018 5th International Conference on Industrial Economics System and Industrial Security Engineering.IEEE,2018:1-6.
[22] SIRCAR R.An introduction to wavelets and other filteringmethods in finance and economics[M].Utah:Academic Press,2002:359.
[23] MALLAT S G.A Theory of Multiresolution Signal Decomposition[J].IEEE,1989,11(7):581-767.
[24] KINGMA D P,BA J.Adam:A Method for Stochastic Optimization [C]//Proceedings of the 3rd International Conference on Learning Representations.2015.
[25] SRIVASTAVA N,HINTON G E,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of Machine Learning Research,2014,15(6):1929-1958.

相关文章 15

[1]	王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[2]	赵冬梅, 吴亚星, 张红斌. 基于IPSO-BiLSTM的网络安全态势预测 Network Security Situation Prediction Based on IPSO-BiLSTM 计算机科学, 2022, 49(7): 357-362. https://doi.org/10.11896/jsjkx.210900103
[3]	来腾飞, 周海洋, 余飞鸿. 视频流的实时景深延拓算法 Real-time Extend Depth of Field Algorithm for Video Processing 计算机科学, 2022, 49(6A): 314-318. https://doi.org/10.11896/jsjkx.201100187
[4]	孙洁琪, 李亚峰, 张文博, 刘鹏辉. 基于离散小波变换的双域特征融合深度卷积神经网络 Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation 计算机科学, 2022, 49(6A): 434-440. https://doi.org/10.11896/jsjkx.210900199
[5]	康雁, 徐玉龙, 寇勇奇, 谢思宇, 杨学昆, 李浩. 基于Transformer和LSTM的药物相互作用预测 Drug-Drug Interaction Prediction Based on Transformer and LSTM 计算机科学, 2022, 49(6A): 17-21. https://doi.org/10.11896/jsjkx.210400150
[6]	王飞, 黄涛, 杨晔. 基于Stacking多模型融合的IGBT器件寿命的机器学习预测算法研究 Study on Machine Learning Algorithms for Life Prediction of IGBT Devices Based on Stacking Multi-model Fusion 计算机科学, 2022, 49(6A): 784-789. https://doi.org/10.11896/jsjkx.210400030
[7]	陈章辉, 熊贇. 基于解耦-检索-生成的图像风格化描述生成模型 Stylized Image Captioning Model Based on Disentangle-Retrieve-Generate 计算机科学, 2022, 49(6): 180-186. https://doi.org/10.11896/jsjkx.211100129
[8]	高堰泸, 徐圆, 朱群雄. 基于A-DLSTM夹层网络结构的电能消耗预测方法 Predicting Electric Energy Consumption Using Sandwich Structure of Attention in Double -LSTM 计算机科学, 2022, 49(3): 269-275. https://doi.org/10.11896/jsjkx.210100006
[9]	邱嘉作, 熊德意. 神经问题生成前沿综述 Frontiers in Neural Question Generation:A Literature Review 计算机科学, 2021, 48(6): 159-167. https://doi.org/10.11896/jsjkx.201100013
[10]	刘嘉琛, 秦小麟, 朱润泽. 基于LSTM-Attention的RFID移动对象位置预测 Prediction of RFID Mobile Object Location Based on LSTM-Attention 计算机科学, 2021, 48(3): 188-195. https://doi.org/10.11896/jsjkx.200600134
[11]	刘奇, 陈红梅, 罗川. 基于改进的蝗虫优化算法的红细胞供应预测方法 Method for Prediction of Red Blood Cells Supply Based on Improved Grasshopper Optimization Algorithm 计算机科学, 2021, 48(2): 224-230. https://doi.org/10.11896/jsjkx.200600016
[12]	彭斌, 李征, 刘勇, 吴永豪. 基于卷积神经网络的代码注释自动生成方法 Automatic Code Comments Generation Method Based on Convolutional Neural Network 计算机科学, 2021, 48(12): 117-124. https://doi.org/10.11896/jsjkx.201100090
[13]	景丽, 何婷婷. 基于改进TF-IDF和ABLCNN的中文文本分类模型 Chinese Text Classification Model Based on Improved TF-IDF and ABLCNN 计算机科学, 2021, 48(11A): 170-175. https://doi.org/10.11896/jsjkx.210100232
[14]	张宁, 方靖雯, 赵雨宣. 基于LSTM混合模型的比特币价格预测 Bitcoin Price Forecast Based on Mixed LSTM Model 计算机科学, 2021, 48(11A): 39-45. https://doi.org/10.11896/jsjkx.210600124
[15]	蒋琪, 苏伟, 谢莹, 周弘安平, 张久文, 蔡川. 基于Transformer的汉字到盲文端到端自动转换 End-to-End Chinese-Braille Automatic Conversion Based on Transformer 计算机科学, 2021, 48(11A): 136-141. https://doi.org/10.11896/jsjkx.210100025

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed