摘要
当前,我国非现金支付对现金支付的替代作用日益显著,但现金支付在居民日常支付中仍占据重要地位。在此背景下,如何精确地预测区域现金需求,保证满足区域现金流通需要已成为一项重要课题。通过借鉴国内外机器学习、神经网络等人工智能技术,基于地区现金投放历史数据,使用岭回归、MLP和LSTM三种模型,构建RR-MLP-LSTM加权组合模型实现了区域现金需求预测,对于统筹货币发行工作、积极防范和化解货币供应风险具有较为重要的借鉴意义。
At present,the substitution effect of non-cash payment to cash payment is increasingly significant.But cash payment still occupies the important position in residents’daily payment.In this context,it has become an increasingly important topic that how to accurately predict regional cash demand to meet the needs of the regional circulation.By learning the application of artificial intelligence technology at home and abroad,such as machine learning and neural network,this paper realizes regional cash demand forecasting by using ridge regression,MLP and LSTM weighted combination model and the historical data of district cash issuance,which has a important reference significance for co-ordinating currency issuing work of the People’s Bank of China and actively preventing and dissolving the risk of currency supply.
出处
《金融理论与实践》
北大核心
2021年第1期52-57,共6页
Financial Theory and Practice
关键词
货币发行
人工智能
神经网络
现金需求预测
currency issue
artificial intelligence
neural network model
cash demand forecasting