Pattern recognition using hidden Markov models in financial time series

Sara Rebagliati, Emanuela Sasso

Abstract


Our aim consists in developing a software which can recognize M trading patterns in real time using Hidden Markov Models (HMMs). A trading pattern is a predefined figure indicating a specific behavior of prices. We trained M + 1 HMMs using Baum-Welch Algorithm combined with Genetic Algorithm. In particular, with HMMs we describe M trading patterns while the other one, called threshold model, can recognize all the not predefined patterns. The classification algorithm correctly recognizes 93% of the provided patterns. Thanks to the analysis of the false positive examples, we finally designed some more filters to reduce them.

Keywords


pattern recognition; hidden Markov models; financial time series; automated trading system

Full Text:

PDF


DOI: http://dx.doi.org/10.12697/ACUTM.2017.21.02

Refbacks

  • There are currently no refbacks.




ISSN 1406–2283 (print)
ISSN 2228–4699 (online)