Application of Improved Convolution Neural Network in Financial Forecasting
- 1 April 2019
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The world economy is in a stage of rapid development, and financial development is also continuing. Financial activities are increasing, and the uncertainty of its changing trend is also increasing. An effective financial forecast can provide a basis for financial planning and decision-making while maintaining the healthy development of financial markets. Convolution neural network is a multilayer neural network structure that simulates the operation mechanism of biological vision system. It is a neural network composed of multiple layers of convolution layers and down sampling layers. It can obtain useful feature descriptions from raw data and is an effective method for extracting features from data. Therefore, this paper introduces the convolution neural network structure to predict the financial time series data, establishes a convolution neural network model, and studies the influence of model parameters on the stock prediction results. Through simulation and comparison, the feasibility and effectiveness of the prediction model given in this paper are verified.Keywords
This publication has 7 references indexed in Scilit:
- Composite Function Wavelet Neural Networks with Differential Evolution and Extreme Learning MachineNeural Processing Letters, 2011
- A locally linear RBF network-based state-dependent AR model for nonlinear time series modelingInformation Sciences, 2010
- Time Series Prediction Based on Linear Regression and SVRPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Nonlinear Predictive Control Using Neural Nets-Based Local Linearization ARX Model—Stability and Industrial ApplicationIEEE Transactions on Control Systems Technology, 2006
- Constrained model predictive control: Stability and optimalityAutomatica, 2000
- Stabilizing Predictive Control of Nonlinear ARX ModelsAutomatica, 1997
- The Nature of Statistical Learning TheoryPublished by Springer Science and Business Media LLC ,1995