Financial time series data prediction method and device

Abstract

The invention discloses a financial time series data prediction method and device, which can be used in the technical field of artificial intelligence. The method comprises the steps: obtaining a plurality of groups of financial time series data in the same time period and reaction time difference data between the groups of financial time series data; performing gray scale transformation on each group of financial time series data to obtain a gray scale image corresponding to each group of financial time series data; according to the response time difference data, translating the grayscale image corresponding to each group of financial time sequence data; performing sequential sliding selection on the time periods by using a window with a preset length, and for each sub-time period, intercepting an image of the time period from each group of grayscale images and arranging the intercepted images in sequence to obtain a combined image; inputting the combined image except the target image into a pre-established generative adversarial network for training; and performing image restoration on a target image by using the trained generative adversarial network, and performing financial time series data prediction. The method can improve prediction accuracy and reduce errors.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method and device for predicting financial time series data. Background technique [0002] In recent years, with the rise of emerging Internet communication methods such as live broadcasts and short videos, financial investment methods such as fund management have been frequently searched and become the focus of people's daily social topics. However, many young investors lack investment experience and investment methods, blindly follow the trend, and the financial market is unpredictable, making them easy to be "cut leeks". The prediction of financial time series data helps investors to understand the future development and changes of related financial products, so as to make further investment decisions and plans. The existing financial time series data forecasting methods have poor forecasting accuracy and large errors, making it difficult to provide investor...

AI Technical Summary

Problems solved by technology

The existing financial time series data forecasting methods have poor forecasting accuracy and large errors, making it difficult to provide investors with effective investment guidance

Images