Algorithm for predicting price rise and fall by combining energy values with big data and application

Abstract

The invention discloses an algorithm for predicting price rise and fall by combining energy values with big data and application. On the basis of a K line graph analyzing the price trend and on the basis of minute chart, subtracting the opening price of each K line from the closing price of each K line to obtain the energy value of each K line; if the energy value is positive, the K line is a positive line, and if the energy value is negative, the K line is a negative line, and the energy values of the K lines at different stages are accumulated to obtain the energy values with different durations, such as extremely short term, short term, middle term, middle and long term, long term and ultra-long term. The method is accurate and timely, can quantify, can quantify rising energy or fallingenergy of different stages, and can also timely enter or reject entry. According to the method, the winning rate of market prediction is relatively high, and after historical big data verification and parameter optimization, an automatic transaction system or index based on an energy value is based on an objective energy value and probability when an automatic transaction (or transaction signal sending) is executed, so that relatively high winning rate guarantee can be achieved.

Description

technical field [0001] The invention relates to the technical field of intelligent data analysis, in particular to an algorithm and application of energy value combined with big data to predict price rise and fall. Background technique [0002] The analysis methods and technical indicators in the existing technology are lagging. At present, the market trend is analyzed or synthesized based on the data analysis or synthesis of a specific period in the past. The trend can only be reflected after a period of time, and the best opportunity to enter the market is often missed . [0003] Secondly, the existing analysis methods are not accurate enough and are relatively subjective. The current methods cannot accurately and quantitatively reflect the magnitude and intensity of real-time price changes, and the current analysis methods such as golden cross dead cross, deviation, and moving average are all subjective. sex factor. [0004] In addition, the existing cycle calculation m...

AI Technical Summary

Problems solved by technology

[0002] The analysis methods and technical indicators in the existing technology are lagging. At present, the market trend is analyzed or synthesized based on the data analysis or synthesis of a specific period in the past. The trend can only be reflected after a period of time, and the best opportunity to enter the market is often missed

[0003] Secondly, the existing analysis methods are not accurate enough and are relatively subjective. The current methods cannot accurately and quantitatively reflect the magnitude and intensity of real-time price changes, and the current analysis methods such as golden cross dead cross, deviation, and moving average are all subjective. sex factor

[0004] In addition, the existing cycle calculation methods are not flexible enough. The current analysis methods are often minute charts, 5-minute charts, hourly charts, daily charts, weekly charts, etc., which are inconvenient to reflect 1.2 hours and 52 minutes. Flexible, convenient for multi-cycle analysis

Images