Stock trend prediction method based on K-line data similarity

Abstract

The invention discloses a stock trend prediction method based on K-line data similarity. The method includes the following steps: step S1, selecting K-line data by a user; step S2, extracting K-line data features according to a preset rule; step S3, retrieving the same features from a database; step S4, judging whether a plurality of similar feature values are matched, if yes, executing a step S6,and otherwise, executing a step S5; step S5, calculating most-similar K-line data; and step S6, extracting K-line data with highest similarity, and carrying out display. According to the method, an algorithm is flexible, an analysis result is precise, and user experience can be improved.

Description

technical field [0001] The invention relates to an intelligent stock prediction method, in particular to a stock trend prediction method based on K-line data similarity. Background technique [0002] The existing stock recommendation system is used to recommend stocks to user terminals and display recommended stocks while interlocking with the server, wherein, when the first condition is met, the controller of the system displays that the strength of the upward trend is 1, and in When the first condition is met and the second condition is met or when the first condition is met and the third condition is met, the controller of the system displays an upward trend strength of 2. In the first condition, the smooth similarity and divergence movement of the stocks stored in the server The average line MACD is equal to or greater than 0, in the second condition, the current stock price is equal to or greater than the sweep baseline and the following span is equal to or greater than...

AI Technical Summary

Problems solved by technology

[0004] Among them, the existing stock recommendation system uses a fixed algorithm to recommend stocks, which cannot guarantee flexibility, because the stock market will fluctuate with the influence of many factors

Among the existing stock plates, there are mechanical and manual classification plates or similar stocks, but many times users cannot clearly understand the trend of stock B from the trend of stock A

These two methods are the existing ideas for stock recommendation, but for users, the experience is very poor, and the function has not been developed according to the actual needs of stock trading users, causing many obstacles for users to use

Images