Multi-line set effective output method

Abstract

The invention provides a multi-line set effective output method, and the method comprises the steps of performing first preset processing on historical target data to obtain a first effective featurevalue; performing second preset processing on the historical target data to obtain a second effective feature value; receiving a strategy execution file input by a user based on the built back test platform; based on the obtained first effective characteristic value, the second effective characteristic value and the received strategy execution file, performing back test on the strategy generated by the strategy platform, and performing back test analysis; and outputting a corresponding dynamic signal according to a back test analysis result. Through the first effective characteristic value, the second effective characteristic value and the strategy execution file, multi-line collection of the basic data is realized, and the effectiveness of the output dynamic signal is improved.

Description

technical field [0001] The invention relates to the technical field of machine learning, in particular to an effective output method for a multi-line set. Background technique [0002] With the development of the digital age, data has become the most important means of production, and with business upgrades, business applications have become more and more complex. Among them, taking stocks as an example, with the development of machine learning, the current multi-line Collective output is being applied faster and faster in the domestic stock and futures markets, but the processing speed of stock or futures-related data in the current existing technology is too slow, and it is unable to update and dynamically adapt new stock or futures data in time, and the current Existing technologies are generally only the application of basic data, and are generally data output for separate processing of basic data. Therefore, it is difficult to adjust the effective output signal accordin...

AI Technical Summary

Problems solved by technology

[0002] With the development of the digital age, data has become the most important means of production, and with business upgrades, business applications have become more and more complex. Among them, taking stocks as an example, with the development of machine learning, the current multi-line Collective output is being applied faster and faster in the domestic stock and futures markets, but the processing speed of stock or futures-related data in the current existing technology is too slow, and it is unable to update and dynamically adapt new stock or futures data in time, and the current Existing technologies are generally only the application of basic data, and are generally data output for separate processing of basic data. Therefore, it is difficult to adjust the effective output signal according to demand.

Images