基于ARIMA-LSTM混合模型的股票短期预测

Stock Short-Term Prediction Based on ARIMA-LSTM Hybrid Model

摘要: 股票数据通常具有复杂性、非线性等特点，传统的股指预测模型难以有效地对股票市场进行分析。本文提出ARIMA模型和LSTM神经网络相结合的ARIMA-LSTM混合模型提取股票数据线性及非线性关系，并对股票数据进行短期预测。通过实际股票数据建模分析表明混合模型的预测效果优于单一的ARIMA模型。

Abstract: The traditional stock index model is usually difficult to analyze the complexity and nonlinear data of the stock market. In this paper, ARIMA-LSTM hybrid model combining Auto-regressive Integrated Moving Average model and Long Short Term Memory Network is proposed to extract the linear and nonlinear relationship of stock data, and make short-term prediction of stock data. The modeling analysis of actual stock data shows that the prediction effect of the hybrid model is better than that of the single Auto-regressive Integrated Moving Average model.