CEEMDAN-based financial time series combination prediction method

Abstract

The invention discloses a financial time series combination prediction method based on adaptive noise complete ensemble empirical mode decomposition (CEEMDAN). According to the method, firstly, a financial time sequence is decomposed into eigenmode function (IMF) sub-sequences and remainders through CEEMDAN; long-term short-term memory (LSTM) is combined with support vector regression (SVR) to construct prediction models which are respectively used for predicting IMF sub-sequences and remainders; and finally, each prediction sequence is reconstructed to obtain a prediction result. Experimentalresults show that the method is suitable for industrial production, single LSTM model, sVR model, compared with other mixed models, the prediction model shows better performance in short-term prediction of the financial time series, and the problems that an existing financial time series prediction method is tedious in process, difficult to directly predict nonlinear and non-stable financial dataand low in prediction accuracy are solved.

Description

technical field [0001] The invention belongs to the field of financial risk management and relates to a financial time series prediction method, in particular to a financial time series combination prediction method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) . Background technique [0002] Stock market price prediction has always been a field of great interest to professional researchers and investors. Stock price changes are nonlinear and non-stationary, and it is very difficult to predict price fluctuations reliably and accurately. From the perspective of forecasting research methods, there are mainly fundamental analysis and technical analysis. Fundamental analysis mainly predicts price trends based on information such as macroeconomic policies, industry development potential, and corporate profitability. Since this method is difficult to quantify, it is difficult to implement. The technical analysis method mainly relies on qu...

AI Technical Summary

Problems solved by technology

[0005] In view of the current situation and existing problems of the above-mentioned existing financial time series prediction methods, the present invention proposes a model combining CEEMDAN, LSTM and SVR to predict financial time series, which overcomes the cumbersome process of the existing financial time series prediction methods and is difficult to deal with nonlinear The problem of direct prediction and low prediction accuracy with unstable financial data

Images