This paper proposes a Markov regime switching framework for modeling carbon emission (CO2) allowances that combines a regime switching behavior and disequilibrium adjustments in the mean process, along with a state-dependent dynamic volatility process. We find that all regime switching based...

This paper attempts to investigate if adopting accurate forecasts from Neural Network (NN) models can lead to statistical and economically significant benefits in portfolio management decisions. In order to achieve that, three NNs, namely the Multi-Layer Perceptron (MLP), Recurrent Neural...