Systems and Methods for Neural Networks Allocating Capital

Abstract

Exemplary systems and methods for allocating capital to trading 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 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.

1 . A method for allocating capital to trading strategies comprising:
 transforming by a virtual machine historical performance data and metrical data into a neural network usable data set;   creating by the virtual machine a neural network base;   forming by the virtual machine a neural network;   training by the virtual machine the neural network for one or more data points; and   calculating by the virtual machine an error rate for the one or more data points until the error rate stops converging or cannot converge.   
     
     
         2 . The method of  claim 1 , further comprising saving by the virtual machine the neural network. 
     
     
         3 . The method of  claim 2 , further comprising testing by the virtual machine the saved neural network against updated metrical and historical data. 
     
     
         4 . The method of  claim 2 , further comprising training by the virtual machine the saved neural network. 
     
     
         5 . The method of  claim 1 , further comprising saving by the virtual machine the neural network as a binary object. 
     
     
         6 . The method of  claim 5 , further comprising transmitting by the virtual machine the binary object to a historical server. 
     
     
         7 . The method of  claim 1 , further comprising activating by a fusion server the neural network. 
     
     
         8 . The method of  claim 7 , further comprising obtaining by the fusion server the historical metrical and the historical performance data. 
     
     
         9 . The method of  claim 8 , further comprising calculating by the fusion server a confidence value. 
     
     
         10 . The method of  claim 8 , further comprising determining by the fusion server whether to execute a trade. 
     
     
         11 . The method of  claim 10 , further comprising performing by the fusion server a survey. 
     
     
         12 . The method of  claim 11 , further comprising determining by the fusion server an order to send to an exchange. 
     
     
         13 . The method of  claim 12 , further comprising sending by the fusion server the order to the exchange. 
     
     
         14 . The method of  claim 13 , further comprising updating by the fusion server to reflect an executed order. 
     
     
         15 . A system for allocating capital to trading strategies comprising:
 a means for transforming historical performance data and metrical data into a neural network usable data set;   a means for creating a neural network base;   a means for forming a neural network;   a means for training the neural network for one or more data points; and   a means for testing a saved neural network against updated metrical and historical data.   
     
     
         16 . The system of  claim 15 , further comprising a means for training the saved neural network. 
     
     
         17 . The system of  claim 15 , further comprising a means for saving the neural network as a binary object. 
     
     
         18 . The system of  claim 17 , further comprising a means for transmitting the binary object to a historical server. 
     
     
         19 . The system of  claim 15 , further comprising a means for activating the neural network. 
     
     
         20 . The system of  claim 15 , further comprising a means for obtaining the historical metrical and the historical performance data.