Search

The recent price volatility in the energy market highlights the importance of financial hedging and the need of its incorporation into an investor's set of portfolio strategies. Realizing the rapid advancement of artificial intelligence, our study empirically examines the use of machine learning models for hedging price risk associated with the holding of energy-based financial product. From a technical perspective, kernel regression and support vector machine are trained to estimate the time-varying optimal hedge ratio given the observed price movement and other factors. The estimated hedge ratio is then employed to guide the price hedging strategy of the crude oil contracts traded in the commodity exchanges. The two machine approaches' hedging effectiveness against price risk is also compared with those of the un-hedged portfolio as well as a well-studied econometric time series approach. Our results indicate that the two forms of learning machines substantially outperform time series model and no-hedging over the out-of-sample period but neither machine dominates another across all testing scenarios. Given these mixed results between kernel regression and support vector machine, we propose and develop a kernel-supervised support vector machine to take advantage of the complementary nature of the two machine learning approaches and enhance the supervised learning process through hierarchical/sequential infusion of information. Cross-learning empirical testing shows that the proposed cross-learning machine is more effective in hedging than individual kernel regression and support vector machine. Furthermore, our study evaluates the impact of incorporating the coefficient of absolute risk aversion and the transaction costs to machine learning models. In general, cross-learning machine outperforms others in all tested scenarios. [ABSTRACT FROM AUTHOR]

In this paper, a group-based fast symbol detection scheme is proposed for massive Group-wise Space-Time Block Code Multiple-Input Multiple-Output systems. The proposed scheme first chooses a number G, (e.g. G=4,6,8) as the size of each group and then conducts the Minimum Mean Square Error (MMSE) detectors to facilitate symbol detection group by group. In particular, instead of directly using huge computational complexity to compute the MMSE detectors, the proposed scheme recursively finds the corresponding assistant matrices to determine the groups and calculate the MMSE detectors. As a result, the transmitted symbols can be recursively estimated group by group. Finally, simulation results and complexity analysis show the proposed scheme performs very close to the existing methods, while using lower computational complexity. [ABSTRACT FROM AUTHOR]

This study analyzes affine styled-facts price dynamics of Henry Hub natural gas price by incorporating the price features of jump risk, and seasonality within stochastic volatility framework. Affine styled-facts dynamics has the advantage of being able to incorporate mean reversion (MR), stochastic volatility (SV), seasonality trends (S), and jump diffusion (J) in a standardized inclusive framework. Our main finding is that models that incorporate jumps significantly improve overall out-of-sample option pricing performance. The combined MRSVJS model provides the best fit of both daily gas price returns and the related cross section of option prices. Incorporating seasonal effects tend to provide more stable pricing ability, especially for the long-term option contracts. [ABSTRACT FROM AUTHOR]