A stock mode automatic identification and prediction method

Abstract

The invention discloses a stock mode automatic identification and prediction method, which detects a graph mode which has occurred in stock market history through a mode identification method, uses the graph mode as training data for training of a support vector machine for stock prediction, and can automatically identify the graph mode and make a transaction decision. The method comprises the following steps of designing a stock market history chart pattern recognition method; carrying out the chart mode feature extraction; training of a vector machine and determination of stock holding timeare supported. The method mainly aims at reducing the problem that traditional manual work is high in cost in chart mode discovery and improving the accuracy rate of a traditional chart mode, the prediction result is more accurate than that of a traditional method, and excessive income can be obtained in a back test experiment.

Description

technical field [0001] The invention belongs to the fields of pattern recognition, machine learning and finance, and relates to a stock pattern automatic recognition and prediction method. Background technique [0002] Among various patterns in the stock market, chart patterns of stock prices are widely used for short-term or long-term forecasting. The chart pattern of the stock price is to draw the historical transaction data of the stock on the chart in different cycles, and then the market performance of the stock in a certain period of time can be expressed to a certain extent by the shape of the chart. Professionals in the financial field have summed up many effective chart patterns after long-term accumulation of experience, such as teacup handle pattern, double bottom pattern, triple bottom pattern, diffusion pattern, triangle pattern, head and shoulders bottom pattern, etc. [0003] With the rapid development of the stock market, the stock market generates massive t...

AI Technical Summary

Problems solved by technology

[0004] 1) There are already a large number of stock selections in the stock market (for example, as of June 2018, there were 3,514 A-share listed companies), and these stocks generate new transaction data every day. Finding target patterns in such large-scale transaction data requires consume a lot of energy;

[0005] 2) Identifying reliable chart patterns requires a lot of experience and professional knowledge, and the limited experience accumulated cannot fully reflect market changes;

[0007] The above practical problems are high cost for a large number of potential investors, and it is difficult to fully implement

Images