Unlock instant, AI-driven research and patent intelligence for your innovation.
A method of automatically generating a transaction policy over a time series
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A time-series, automatic generation technology, applied in the field of financial technology, can solve a large number of labor costs and other problems, achieve the effect of reducing workload and improving research efficiency
Pending Publication Date: 2019-05-03
周鸣籁
View PDF4 Cites 2 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
Therefore, researching both machine learning-based trading strategies and rule-based trading strategies requires a lot of human cost
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0045] Such as figure 1 , this embodiment provides a mechanism for automatically generating a time series-based trading strategy based on machine learning:
[0046] (1) Establish a factor library and determine the use of a neural network model.
[0047] (2) Given that the target is the one-hour line of the Shanghai Composite Index, first randomly select 5 factors X from the factor library 1，1， , X 1，2 , X 1，3 , X 1，4 , X 1，5, which are MA (real, time period), head and shoulders pattern (open, high, low, close), MA (real, time period), price change rate (close), ATR (high, low, close, time period). After the factor is instantiated, it is MA (close, timeperiod=5), head and shoulders pattern (open, high, low, close), MA (open, timeperiod=10), price change rate (close), ATR (high, low, close, timeperiod=8); Randomly select a prediction target factor Y 1 is SharpeRatio(close, timeperiod). After instantiation, it is SharpeRatio(close, timeperiod=4).
[0048] MA factor: real...
Embodiment 2
[0077] Such as image 3 , this embodiment provides a mechanism for automatically generating a rule-based trading strategy on time series:
[0078] (1) Establish factor library.
[0079] (2) Given the one-hour line of the Shanghai Composite Index, first randomly select 5 factors X from the factor library 1，1， , X 1，2 , X 1，3 , X 1，4 , X 1，5 , which are MA (real, time period), head and shoulders pattern (open, high, low, close), MA (real, time period), price change rate (close), ATR (high, low, close, time period). After the factor is instantiated, it is MA (close, timeperiod=5), head and shoulders pattern (open, high, low, close), MA (open, timeperiod=10), price change rate (close), ATR (high, low, close, timeperiod=8).
[0080] MA factor: real is an unspecified vector, which can randomly take values such as open, high, low, close, volume, amount, etc. timeperiod is an unspecified scalar of int type, so an int value is taken randomly. The output value of the MA facto...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
PUM
Login to View More
Abstract
The invention relates to a method for automatically generating a transaction strategy on a time sequence. K groups of factors are randomly extracted from the factor library, machine learning or rule-based mapping from m factors to transaction signals is randomly generated for each group of factors, and back testing is carried out, so that k groups of machine learning-based transaction strategies or rule-based transaction strategies are generated; iteratively evolving the k groups of transaction strategies to finally obtain a transaction strategy meeting expected revenue risk requirements. Through iterative evolution, various transaction strategies meeting the expected revenue risk requirements of the user can be generated, and the workload of transaction strategy researchers is reduced; alocal optimal solution of the factor combination can be mined for reference of researchers; the problem of insufficient fund capacity of a single transaction strategy can be solved by generating transaction strategies on a large scale in batches; meanwhile, a transaction strategy with low correlation with an original transaction strategy can be generated, and the stability of fund income is improved.
Description
technical field [0001] The invention relates to a method for automatically generating a trading strategy on a time series, which belongs to the field of financial technology. Background technique [0002] Quantitative investment refers to a trading method that issues buying and selling orders through quantitative methods and computer programming to obtain stable returns. In a broad sense, quantitative investment can be divided into relative value transactions and directional transactions in time series. Traditionally distinguished by method, directional trading on time series can be divided into machine learning-based trading strategies and rule-based trading strategies. [0003] In machine learning-based methods, researchers first identify groups of factors (called features in the field of machine learning) and their corresponding factor parameters, a predictive target factor (such as the price change in the next hour or the next day, or the Sharpe ratio) and Its correspo...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to View More 
Login to View More 
