Big Data

Constrained Mixture Models For Asset Returns Modelling

Download Now Date Added: Mar 2011
Format: PDF

The estimation of asset return distributions is crucial for determining optimal trading strategies. In this paper, the authors describe the constrained mixture model, based on a mixture of Gamma and Gaussian distributions, to provide an accurate description of price trends as being clearly positive, negative or ranging while accounting for heavy tails and high kurtosis. The model is estimated in the Expectation Maximisation framework and model order estimation also respects the model's constraints.