基于MF-LSTM的上市公司现金流预测研究
Research on Cash Flow Forecast of Listed Companies Based on MF-LSTM
江泽茹 1王冉冉2
作者信息
- 1. 北京大学政府管理学院,北京 100871
- 2. 北京大学大数据分析与应用技术国家工程实验室,北京 100871;北京大学重庆大数据研究院,重庆 401121
- 折叠
摘要
企业现金流量很大程度上反映着企业的生存和发展能力,现金流的预测和分析对于投资者和市场管理者都具有十分重要的现实意义.本文利用我国A股上市公司2012年至2019年的财务数据和账户数据,提出混合频率长短时记忆神经网络模型(Mixed Frequency Long Short Term Memory,MF-LSTM)对上市公司现金流量进行预测.通过神经网络结构设计,本文将不同频率数据进行了有效混合,预测结果明显优于传统时间序列模型.另外,实验结果还验证了企业账户数据是现金流预测的有效解释变量.
Abstract
Cash flow can reflect survival and development potential of companies.For both investors and managers,the prediction and analysis of cash flow is of great practical significance.Based on finan-cial data and account data of China's A-share listed companies from 2012 to 2019,this paper designs Mixed Frequency Long Short Term Memory(MF-LSTM)neural networks to predict cash flow of listed companies.By designing the structure of the network,mixed frequency information is combined effec-tively.Compared with traditional time series models,our models enjoy better performance significantly.In addition,experimental results show that account data is an effective explanatory variable for cash flow prediction.
关键词
现金流/时间序列预测/混频模型/LSTMKey words
cash flow/time series forecasting/mixed frequency model/LSTM引用本文复制引用
出版年
2024
NETL
NSTL
万方数据