A context-aware measurement method and system for financial high-frequency trading data

Abstract

The invention belongs to the field of information technologies, and particularly discloses a method and a system for measuring scene awareness for financial high-frequency transaction data. The method includes steps of 1, creating a financial high-frequency transaction database; 2, creating a scene association rule base; 3, computing the scene awareness; 4, feeding results and updating rules. The system comprises four corresponding modules. By the aid of the method and the system, influence of scene impact generated by macro-economic environments, natural environments and financial policy events on high-frequency transaction is computed from a scene awareness angle, so that financial high-frequency transaction operational decision reference is provided for a user, and purposes of avoiding risks and effectively gaining profits are achieved. The method and the system have the advantages that dynamic effects which are generated for the financial high-frequency transaction by the macro-economic environments, the natural environments and the financial policy events are comprehensively considered, so that the user can make a judgment on investment advantageously; the system is provided with a feedback mechanism, the scene association rule base can be continuously improved, and accordingly the computed results are accurate.

Description

technical field [0001] The invention belongs to the field of information technology, and in particular relates to context-aware computing technology, in particular to a context-aware measurement method and system for financial high-frequency transaction data. Background technique [0002] In the financial and economic market, more and more scholars have begun to pay attention to the research of high-frequency financial transaction data, dig deep into the hidden characteristics of high-frequency financial data to discover the microeconomic laws of the financial market, and provide investors with investment prediction decisions refer to. At present, many researchers study high-frequency trading data from the perspective of statistical econometric analysis, explore its statistical characteristics and laws from the external performance of the data, and conduct modeling and analysis. However, high-frequency financial data are largely disturbed by microstructure noise and have dy...

AI Technical Summary

Problems solved by technology

[0003] 1. Financial high-frequency data are often difficult to meet the requirements of better statistical testing, the calculation results have large errors, and the prediction accuracy is not high;

[0004] 2. It is difficult to make a good description of the impact of changing scenarios and the interference of microstructure noise. Without the feedback mechanism of the above information, it is impossible to self-correct and improve the selected model

Images