Filtering and forecasting commodity futures prices under an HMM framework

- We develop a parsimonious model for arbitrage-free futures prices.
- The model features a multivariate regime-switching framework.
- HMM filtering algorithms yield self-tuning parameters.
- Statistical validation was carried out through a numerical demonstration.

We propose a model for the evolution of arbitrage-free futures prices under a regime-switching framework. The estimation of model parameters is carried out using the hidden Markov filtering algorithms. Comprehensive numerical experiments on real financial market data are provided to illustrate the effectiveness of our algorithm. In particular, the model is calibrated with data from heating oil futures and its forecasting performance as well as statistical validity is investigated. The proposed model is parsimonious, self-calibrating and can be very useful in predicting futures prices.