Rita Laura D'Ecclesia

Forecasting Energy Commodity Prices Using Neural Networks

A new machine learning approach for price modeling is proposed. The use of neural networks as an advanced signal processing tool may be successfully used to model and forecast energy commodity prices, such as crude oil, coal, natural gas, and electricity prices. Energy commodities have shown explosive growth in the last decade. They have become a new asset class used also for investment purposes. This creates a huge demand for better modeling as what occurred in the stock markets in the 1970s. Their price behavior presents unique features causing complex dynamics whose prediction is regarded as a challenging task. The use of a Mixture of Gaussian neural network may provide significant improvements with respect to other well-known models. We propose a computationally efficient learning of this neural network using the maximum likelihood estimation approach to calibrate the parameters. The optimal model is identified using a hierarchical constructive procedure that progressively increases the model complexity. Extensive computer simulations validate the proposed approach and provide an accurate description of commodities prices dynamics.

Term structure of interest rates and the expectation hypothesis: The euro area

Abstract This paper investigates the informational content of the yield curve in the European market using data on the Italian term structures. According to the expectation hypothesis theory (EHT) the current forward rate equals the future short rate plus a constant risk premium that is time invariant but maturity dependent. This theory has been widely tested in the empirical literature providing various findings according to the country where it has been applied and to the segment of the yield curve examined or the period under study. The standard approach to test the EHT uses the regression techniques assuming data on spot rates and their first differences to be stationary. Recently an increasing number of studies evidenced the non stationarity of interest rates time series and some tests of the EHT are formulated using term spread and forward-spot spread which are stationary. A new strand of literature suggests to investigate the EHT using a restricted VAR framework. In this paper, following [Jondeau, E., Ricart, R., 1999. The expectations hypothesis of the term structure: tests on us, german, french and uk euro-rates. Journal of International Money and Finance 18, 725–750, Ghazali, N.A. Low, S.W., 2002. The expectations hypothesis in emerging financial markets: the case of malaysia. Applied Economics 34, 1147–1156 and Seo, B., 2003. Non linear mean reversion in the term structure of interest rates. Journal of Economic Dynamics and Control 27, 2243–2265], we test if the expectation hypothesis holds using cointegration and error correction analysis. For the period under study results suggest that the long and short term interest rates are cointegrated and therefore subject to a long equilibrium path, providing evidence that the EHT holds for the Italian and the European market.

Subband prediction of energy commodity prices

The dynamics of commodity prices has become a major field of analysis in the last 20 years. Standard econometric procedures to describe the behavior of prices have not been able to provide accurate description of the real dynamics. In this paper we apply filter banks to predict prices of specific energy commodities: crude oil, natural gas and electricity, which play a crucial role in the international economic and financial context. Given the high volatility of energy commodity prices, an accurate short term prediction allows to set adequate risk management strategies for producers, retailers and consumers. Filter banks for subband decompositions of the sequences to be predicted are proposed in the paper, allowing the implementation of a parallel computing system to get faster and more accurate implementation. The prediction system is based on a neural model trained on each subband according to specific training and prediction techniques.

A study on crude oil prices modeled by neurofuzzy networks

In the last decade the increasing volatility of petroleum markets has challenged time series analysts to produce highly predictive models. Crude Oil is a major driver of the global economy and its price fluctuations are a key indicator for producers, consumers and investors. With investors following the longerterm upward trend in Energy prices Commodity investments, we believe this will drive an increasing importance for methodologies like neurofuzzy networks for risk quantification, measurement and management. The data used is Crude Oil prices for both Brent and WTI in the 10 year period from 2001 to 2010. We will prove that the neurofuzzy approach based on ANFIS networks compare favorably with respect to other standard and neural models and it is able to achieve useful performances in terms of accurate prediction of prices and their probability distribution.

Long swings in exchange rates: a stochastic control approach

A regime-switching model to describe the exchange rate dynamics is derived as solution to a stochastic control problem. We assume exchange rates evolve according to some macroeconomic variables (fundamental) whose dynamics could be described by a Brownian motion with a state-dependent drift. The local Monetary Authority is assumed to intervene influencing the evolution of the fundamental, causing the exchange rate to switch from a depreciating to an appreciating regime (and vice versa). We assume the behaviour of the Monetary Authority can be modeled using an optimal control framework where the state variable is represented by the fundamental. The solution of the model allows the determination of an endogenous tolerance band within which the exchange rate freely fluctuates.

Estimation of asset demands by heterogeneous agents

We develop optimization models to analyze the demand for financial assets by heterogeneous agents. The models extend Frankels [J. Portfolio Manage. 11 (4) (1985) 18] earlier approach, and relax the assumption of normality of asset returns. Instead, we assume that investors maximize an expected utility of terminal wealth based on heterogeneous attitudes toward risk. Solving a bi-level optimization program, we endogenously estimate the risk aversion parameters and derive the optimal asset holdings for each agent. The models are tested on United States market data, explaining the market structure better than previously postulated models.

A disutility-based drift control for exchange rates

In this article we propose an exchange rate model as a solution to the disutility-based drift control problem. Given that the exchange rate is a function of the fundamental, we assume that government authorities control the fundamental dynamics aimed at minimizing the discounted expected disutility caused by the distance between the fundamental and some specific target. The theoretical model is solved using the dynamic programming approach and introducing the concept of viscosity solution. We contribute to research on exchange rate control policies by deriving the optimal interventions aimed at stabilizing the exchange rate and preserving macroeconomic stability. We also show that, under particular conditions, it is possible to derive the optimal width of the currency band.