Financial market prediction method based on complex network

Abstract

The invention discloses a financial market prediction method based on a complex network and relates to the technical field of finance and computer cross research. A complex network is constructed to represent listed companies and following, departing, co-occurrence and other relationships between the listed companies. The method comprises the following steps of based on complex networks of listedcompanies, selecting information of a plurality of companies closest to a listed company as a prediction basis and using the prediction results as output; constructing a prediction model based on deeplearning; the model comprises an encoder-decoder structure and a convolutional neural network structure with an attention mechanism. The embedding of the related companies and the historical performance data of the companies are taken as input, and the financial index trend of the related companies is taken as output, so that the accuracy of financial index prediction of the listed companies canbe remarkably improved, the performance of the listed companies on the financial market in the future can be judged more accurately, and investment and management decisions can be made better.

Description

technical field [0001] The invention relates to the technical field of financial and computer cross research, in particular to a method for predicting financial markets based on complex networks. Background technique [0002] The financial market such as the stock market is a barometer of the economy. How the financial market will fluctuate and how the company will perform is a matter of great concern to economic management departments, financial institutions, enterprises and investors. How to effectively predict the performance of the financial market is an important issue in the business world and Academia has received extensive attention. [0003] Existing analysis and prediction methods do not consider the relationship between listed companies enough. When predicting a company's financial indicators, they only consider the information of the company to be predicted in isolation, and do not consider the mutual influence between companies. Contents of the invention [0...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the fact that the existing analysis and prediction methods do not consider the relationship between listed companies enough, the present invention only considers the information of the company to be predicted in isolation when predicting the financial index of a company, and does not consider the mutual influence between companies Shortcomings, the technical problem to be solved by the present invention is to provide a financial market prediction method based on a complex network, how to represent the relationship between listed companies and between listed companies and sections, concepts, and use this information to carry out financial forecasting of listed companies. Index Forecast

Images