CAJ | 학술논문

随着经济的发展，股票投资已成为很多人的一种投资理财方式，而股票价格的预测也成为投资者关心和研究的焦点。建立一个运算速度和精确度都比较高的股价预测模型，对于金融投资者具有理论指导意义和实际应用价值。文中针对传统BP算法存在的学习速度慢、容易陷入局部极小值、隐层数不易确定等问题，使用三次样条权函数神经网络建立股价预测模型，克服了传统神经网络的缺点。仿真结果表明，该模型具有较高的预测精度，能够对股市进行有效的预测。
수착경제적발전，고표투자이성위흔다인적일충투자리재방식，이고표개격적예측야성위투자자관심화연구적초점。건립일개운산속도화정학도도비교고적고개예측모형，대우금융투자자구유이론지도의의화실제응용개치。문중침대전통BP산법존재적학습속도만、용역함입국부겁소치、은층수불역학정등문제，사용삼차양조권함수신경망락건립고개예측모형，극복료전통신경망락적결점。방진결과표명，해모형구유교고적예측정도，능구대고시진행유효적예측。
With economic development,stocks have become a way of finance and investment for many people,and the stock price forecas-ting has become the focus of investors' attention and study. Establishing a stock price forecasting model with high computing speed and accuracy has theoretical and practical significance for financial investors. As the traditional BP algorithm has problems such as low learn-ing speed,easy to fall into local minimum value,difficult to determine the number of hidden layer neurons,the stock prediction model is established using the neural networks with cubic spline weight functions to overcome the shortcomings of traditional neural networks. The simulation results show that the model has high accuracy and can effectively predict the stock market.