Forecast Of Yield Of Sse Composite Index Based On WaveNet Convolutional Model With Conditional Time Series

With the development of the economy,the position of the securities market in the market economy has become more prominent.It can provide sufficient cash flow for enterprises and meet the high-yield requirements of investors.Therefore,the forecast of the securities market trend is very important.Effective forecasting can make the initiatives of the state,enterprises and investors more forward-looking,so that everyone can make better use of positive trends and better respond to negative trends.This paper first summarizes the three stages of financial forecasting technology development and analyzes the traditional methods used to predict financial time series.Under the background of bottlenecks and defects in traditional prediction models,this paper introduces a deep learning model in the field of artificial intelligence speech analysis.By adding an identity map,the convolutional layer of the ordinary convolutional neural network is changed to the residual element structure,and finally constructs the WaveNet convolution model with conditional time series specifically for financial forecasting.In order to improve the quality of input data and ensure the comprehensiveness of information,this paper comprehensively analyzes various factors that affect the future trend of the securities market,and divides these factors into market transactions,macroeconomic and economic factors,other financial product market,other countries’ securities market and investor confidence,and then use Wind Financial Platform to screen out the condition variables of Shanghai Composite Index yield forecasting.In the empirical prediction research,the model has achieved good prediction results;the real market transactions based on this model have also achieved good returns.