统计与决策2023，Vol.39Issue(23)：34-39,6.DOI:10.13546/j.cnki.tjyjc.2023.23.006
基于LSTM的政策效应预测模型及其应用
LSTM-based Policy Effect Prediction Model and Its Application
摘要
Abstract
This paper proposes a policy evaluation method based on Long Short-Term Memory(LSTM)neural network,which combines deep learning techniques and counterfactual inference prediction.First,the LSTM method is used to fit the complex re-lationship between the group variables before the policy intervention,and then the counterfactual inference results of the group variables after the policy intervention are predicted.On this basis,the average treatment effect of the policy program is measured.Finally,the model error effect is eliminated and the economic effect of the policy scheme is evaluated.Taking the preferential loan interest rate policy of import and export of Hubei Province as an example,the paper estimates the macroeconomic benefits brought by the preferential loan policy.The results show that the LSTM-based method is superior to SCM-LASSO and ANN artificial neu-ral network in forecasting accuracy,and that the correction of model error effect can significantly improve the evaluation accuracy of policy effect.关键词
政策效应评估/长短期记忆神经网络/优惠贷款利率/误差效应Key words
policy effect assessment/LSTM neural network/preferential loan interest rate/error effect分类
管理科学引用本文复制引用
李树娴,张晓骏,胡成雨..基于LSTM的政策效应预测模型及其应用[J].统计与决策,2023,39(23):34-39,6.基金项目
国家自然科学基金资助项目(71974204) （71974204）
教育部人文社会科学研究基金项目(22YJAZH038) （22YJAZH038）
科技大数据湖北省重点实验室开放基金资助项目(E3KF291001) （E3KF291001）
