Stock forecasting method and system based on LSTM model

Abstract

The present invention discloses a stock forecasting method and a system based on an LSTM model, which belong to the technical field of stock forecasting. The technical method of the invention comprises: grabbing the stock data of a large enterprise in a recent period through establishing a deep learning environment; making a pre-phase analysis of the stock data; re-extracting the key characteristics; selecting the training data; inputting the training data; constructs a stock forecasting model based on the deep learning theory wherein the stock forecasting model comprises an input layer, a hidden layer and an output layer; and finally outputting a forecasting result and in combination with the true value, using the error percent as an evaluation index for evaluations. The invention also realizes a stock forecasting system based on the LSTM model. The invention adopts the LSTM model to construct a stock forecasting model, which is suitable for the periodically strong data and sequence data, solves the long-term dependence problem, and is more flexible than a traditional time sequence model.

Description

technical field [0001] The invention belongs to the field of stock forecasting, and more specifically relates to a stock forecasting method and system based on an LSTM model. Background technique [0002] With the development of the Internet industry, information technology dominates, and the securities market is developing towards a modern market. Now there are more than a few thousand listed companies in Shanghai and Shenzhen. However, the income and risk of stock investment are often directly proportional, that is, the higher the investment income, the greater the risk you may take. Therefore, the research on stock market forecasting methods has extremely important application value and theoretical significance. There have always been many traditional analysis techniques. It should be said that these traditional technical analysis methods have made great achievements in stock analysis. However, it is not difficult to find that these existing theories and methods also hav...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above defects or improvement needs of the prior art, the present invention provides a stock forecasting method and system based on the LSTM model. The model builds a deep learning model on the previous stock trend to predict the future stock trend, thereby solving the technical problems of poor extrapolation, poor accuracy, large amount of calculation, and easy over-fitting of the existing forecasting technology

Images