Stock risk early warning system based on blockchain, big data and algorithms

Abstract

A stock risk early warning system based on block chain, big data and algorithm, including a stock forecast model building module, a block chain storage module and a stock forecast module, the stock forecast model building module is used to set up a stock forecast model, and the block The chain storage module is used to store the sample set used for training and testing the stock prediction model, and the stock prediction module intercepts the historical index data of the previous trading day and the previous trading day according to the preset subsequence length to form a subsequence, and The normalized subsequence is used as an input value and input into the established stock forecasting model, and the output value of the stock forecasting model is the stock trend on the forecasting day. Beneficial effects of the present invention: use the stock historical index data to train and test the BP neural network, establish a stock prediction model based on the BP neural network to predict the stock trend, so that investors can avoid investment losses in time according to the predicted stock rise and fall trend .

Description

technical field [0001] The invention relates to the financial field, in particular to a stock risk early warning system based on blockchain, big data and algorithms. Background technique [0002] With the rapid development of the process of global economic integration, the stock market plays an increasingly important role in the global economy, and accurate forecasting of the stock market has important social and economic value. The stock market has massive and heterogeneous data from a wide range of sources. With the development of information technology, the use of data mining algorithms can dig out potential and valuable knowledge and information in the data to support management and decision-making activities. Through data mining and predictive analysis, we can understand the future trend of the stock market, which can help investors adjust their investment strategies, and can avoid investment losses in time according to the predicted stock ups and downs. [0003] With ...

AI Technical Summary

Problems solved by technology

The BP neural network model has the advantages of strong nonlinear mapping ability and strong fault tolerance, but it also has the defects of being sensitive to the initial value and easy to fall into local optimum. It has the defect of unstable prediction accuracy. In view of the above defects, the cuckoo algorithm is proposed to optimize the initial weight and threshold of the BP neural network, which makes up for the shortcomings of the BP neural network that are sensitive to the initial value and easy to fall into local extremum. When the optimized BP neural network is applied to stock forecasting, it has high forecasting accuracy, which can play an early warning role

Images