Cover Page    Full-Text Download    
Subscribe Now
Recommend the Paper
Stale model detection for algorithmic trading  
CARLOS NOCITO1,Miroslav Kubat2

Department of Electrical and Computer Engineering

University of Miami

Miami, Fl

*1, Email : c.nocito@umiami.edu

2, Email : mkubat@miami.edu 

 
Abstract .The use of data mining and adaptive learning is a very controversial issue among the algorithmic trading community in the financial world. The reason for the mistrust in the techniques arrives from some very well-known problems: overfitting to training data and insufficient support for the derived models. In this paper, we present a new element to the use of some classic data mining and adaptive learning algorithms: a set of objective distance measurements that track the similarity between the prediction model and the actual system. We use historical market data to develop algorithms, and investigate the correlation between prediction accuracy of the models and their distance measurements. We find that this tracking could allow investors to discard stale models earlier, thus decreasing losses.
 
Keywords : algorithmic trading; decision trees; performance tracking; data mining; jensen-shannon; kullback-leibler
 URL: http://dx.doi.org/10.7321/jscse.v3.n3.52  
 
 

Subscribe Now

Email :    
Subscribe to receive free TOC's JSCSE by email
Subscribe

Recommend To Friend

Email :     People