High-frequency trading strategies using wavelet-transformed order book information and dynamic Bayesian networks

Abstract

This paper presents a feature vector representing intraday USD/COP transaction prices and order book dynamics using zig-zag patterns. A Hierarchical Hidden Markov Model is used to capture the market sentiment dynamics choosing from uptrend or downtrend latent regimes based on observed feature vector realizations calculated from transaction prices and wavelet-transformed order book volume dynamics. The HHMM learned a natural switching buy/uptrend sell/downtrend trading strategy using a training-validation framework over one month of market data. The model was tested on the following two months, and its performance was reported and compared to results obtained from randomly classified market states and a feed-forward Neural Network. This paper also separately assessed the contribution to the model's performance of the order book information and the wavelet transformation.