AI helps you reading Science

AI generates interpretation videos

AI extracts and analyses the key points of the paper to generate videos automatically


pub
Go Generating

AI Traceability

AI parses the academic lineage of this thesis


Master Reading Tree
Generate MRT

AI Insight

AI extracts a summary of this paper


Weibo:
At step 101, a virtual machine is generated by a master virtual machine server for a trading strategy in a his torical server

Systems and Methods for Allocating Capital to Trading Strategies for Big Data Trading in Financial Markets

(2015)

Cited by: 0|Views8
Full Text
Bibtex
Weibo

Abstract

0004 Provided herein are exemplary systems and meth ods for allocating capital to trading strategies, including gen erating a virtual machine by a master virtual machine server for a trading strategy in a historical server, obtaining histori cal performance data for the trading strategy from the histori cal server, transforming by the vir...More

Code:

Data:

Introduction
  • 0005 Exemplary systems and methods may further com prise training by the virtual machine a neural network for one or more data points, calculating by the virtual machine an error rate for the one or more data points until the error rate stops converging or cannot converge, saving by the virtual machine the neural network, testing by the virtual machine the saved neural network against updated metrical and his torical data, training by the virtual machine the saved neural network, saving by the virtual machine the neural network as a binary object, transmitting by the virtual machine the binary object to the historical server, activating by a fusion server the neural network, obtaining by the fusion server historical met rical and historical performance data, calculating by the fusion server a confidence value, determining by the fusion server whether to execute a trade, performing by the fusion server a Survey, determining by the fusion server an order to send to an exchange, sending by the fusion server the order to the exchange and updating by the fusion server to reflect an executed order.
  • A neural network base comprises various algorithms designed to interact with a data set in order to determine if a particular trading strategy should be employed during the trading period.
Highlights
  • 0004 Provided are exemplary systems and meth ods for allocating capital to trading strategies, including gen erating a virtual machine by a master virtual machine server for a trading strategy in a historical server, obtaining histori cal performance data for the trading strategy from the histori cal server, transforming by the virtual machine the historical performance data into metrical data, transforming by the Vir tual machine the historical performance data and metrical data into a neural network usable data set, creating by the virtual machine a neural network base, and forming by the virtual machine a neural network
  • 0005 Exemplary systems and methods may further com prise training by the virtual machine a neural network for one or more data points, calculating by the virtual machine an error rate for the one or more data points until the error rate stops converging or cannot converge, saving by the virtual machine the neural network, testing by the virtual machine the saved neural network against updated metrical and his torical data, training by the virtual machine the saved neural network, saving by the virtual machine the neural network as a binary object, transmitting by the virtual machine the binary object to the historical server, activating by a fusion server the neural network, obtaining by the fusion server historical met rical and historical performance data, calculating by the fusion server a confidence value, determining by the fusion server whether to execute a trade, performing by the fusion server a Survey, determining by the fusion server an order to send to an exchange, sending by the fusion server the order to the exchange and updating by the fusion server to reflect an executed order
  • 0006 An exemplary system for allocating capital to trad ing strategies may include a means for generating a virtual machine for a trading strategy in a historical server, a means for obtaining historical performance data for the trading strat egy from the historical server, a means for transforming the historical performance data into metrical data, a means for transforming the historical performance data and metrical data into a neural network usable data set, a means for creat ing a neural network base, and a means for forming a neural network
  • According to further exemplary embodiments, the system may include a means for training by the neural net work for one or more data points, a means for calculating an error rate for the one or more data points until the error rate stops converging or cannot converge, a means for saving the neural network, a means for testing the saved neural network against updated metrical and historical data, a means for training the saved neural network, a means for saving the neural network as a binary object, a means for transmitting the binary object to the historical server, a means for activat ing the neural network, a means for obtaining historical met rical and historical performance data, a means for calculating a confidence value, a means for determining whether to execute a trade, a means for performing a Survey, a means for determining an order to send to an exchange, a means for sending the order to the exchange, and a means for updating to reflect an executed order
  • At step 101, a virtual machine is generated by a master virtual machine server for a trading strategy in a his torical server
Results
  • An updated historical and metrical data set comprises historical and metrical data col lected since the time the virtual machine created the neural network at step 105.
  • If the observed error rate does not converge, the neural network 203 is dropped and marked as “unusable' for the one or more historical data and metrical data points for the tradable item employing a particular strategy.
  • 1. A method for allocating capital to trading strategies comprising: generating a virtual machine by a master virtual machine server for a trading strategy in a historical server; obtaining historical performance data for the trading strat egy from the historical server, transforming by the virtual machine the historical perfor mance data into metrical data; transforming by the virtual machine the historical perfor mance data and metrical data into a neural network usable data set; creating by the virtual machine a neural network base; and forming by the virtual machine a neural network.
  • 5. The method of claim 4, further comprising: testing by the virtual machine the saved neural network against updated metrical and historical data.
  • A system for allocating capital to trading strategies comprising: a means for generating a virtual machine for a trading strategy in a historical server; a means for obtaining historical performance data for the trading strategy from the historical server, a means for transforming the historical performance data into metrical data; a means for transforming the historical performance data and metrical data into a neural network usable data set; a means for creating a neural network base; and a means for forming a neural network.
Conclusion
  • The system of claim 19, further comprising: a means for saving the neural network; a means for testing the saved neural network against updated metrical and historical data; a means for training the saved neural network; a means for saving the neural network as a binary object; a means for transmitting the binary object to the historical server; a means for activating the neural network; a means for obtaining historical metrical and historical performance data; a means for calculating a confidence value; a means for determining whether to execute a trade; a means for performing a Survey: a means for determining an order to send to an exchange; a means for sending the order to the exchange; and a means for updating to reflect an executed order.
  • A master virtual machine server may comprise a single server responsible for generating all of or most of the described virtual machines
Author
howard m getson
howard m getson
sean vallie
sean vallie
adam peterson
adam peterson
kelvin rodriguez
kelvin rodriguez
Your rating :
0

 

Tags
Comments
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科