Short-period share price prediction algorithm based on IPSO-BP neural network

Abstract

The invention discloses a short-period share price prediction algorithm based on an IPSO-BP neural network. The algorithm includes the following steps: sampling historical data and constructing a sample data set; conducting normalization processing on the sample data set and mapping the data to the same interval; conducting fitting and cyclic iteration on the normalized data, and predicting future sample data; determining the number of layers of a network, the number of neurons of each layer, and a BP network parameter and an activation function, dynamically changing inertia weights and learning factors in order from the highest to the lowest, and constructing an IPSO-BP neural network; and according to the future sample data, utilizing the IPSO-BP neural network to predict stock data. The short-period share price prediction algorithm improves the precision, and can effectively increase the convergence speed of the overall network.

Description

technical field [0001] The invention relates to a short-term stock price prediction algorithm based on IPSO-BP neural network. Background technique [0002] Stocks, as a kind of securities, contain economic benefits and can be circulated and transferred through listing. At the same time, when a joint stock limited company raises capital, it can reflect the holder's (that is, shareholders') part of the company by issuing shares to each shareholder. Ownership of an asset. The emergence of the trading market can be traced back to the 1960s, and the United States is the earliest place where the modern trading market appeared. The openness of the world's economic and financial markets has increased rapidly since China's accession to the WTO. At the same time, the international market has provided more and more opportunities and space for Chinese companies to list abroad. Therefore, the role of China's securities market in my country's economic development appear more and more im...

AI Technical Summary

Problems solved by technology

However, in the process of practical application, the neural network algorithm also has some obvious limitations: one is that it is easier to fall into local extreme points, and the other is that the convergence speed is slow. These limitations greatly reduce the application range of the neural network algorithm, that is, only It can solve simple and small-scale problems, and the final result obtained is also likely to be a local optimal solution, so that the application of BP (Back Propagation) neural network can effectively predict the ultra-short-term stock price. restricted

Images