Published Papers

This paper reproduces the performance of an international market capitalization shipping stock index and two physical shipping indexes by investing only in US stock portfolios. The index-tracking problem is addressed using the differential evolution algorithm and the genetic algorithm. Portfolios are constructed by a subset of stocks picked from the shipping or the Dow Jones Composite Average indexes. To test the performance of the heuristics, three different trading scenarios are examined: annually, quarterly and monthly rebalancing, accounting for transaction costs where necessary. Competing portfolios are also assessed through predictive ability tests. Overall, the proposed investment strategies carry less risk compared to the tracked benchmark indexes while providing investors the opportunity to efficiently replicate the performance of both the stock and physical shipping indexes in the most cost-effective way.

Following the importance of gold in the global economy and the high interest that has attracted recently, the objective of this paper is twofold: to predict the price of gold by using the Adaptive Neuro-Fuzzy Inference System (ANFIS) and compare its forecasting accuracy with various time-series forecasting methods and the 'Buy and Hold' (B&H) strategy. The results show that the ANFIS's accuracy is far superior to the performance of all compared methods and therefore ANFIS demonstrates the potential of neuro fuzzy-based modelling for predicting the gold's price.

In this article the financial/ownership structures of agribusiness cooperatives are analyzed to examine whether new cooperative models perform better than the more traditional ones. The assessment procedure introduces a new financial decision-aid approach, which is based on data-analysis techniques in combination with a preference ranking organization method of enrichment evaluations (PROMETHEE II). The application of this multicriteria decision-aid approach allows the rank ordering of cooperatives based on the most prominent financial ratios. The financial ratios were selected using principal component analysis. This analytical procedure reduces the dimensionality of large numbers of interrelated financial performance measures. We assess the financial success of Dutch agribusiness cooperatives for the period 1999-2010. Results show that there is no clear-cut evidence that cooperative models used to attract extra members' investments and/or outside equity perform better than the more traditional models. This suggests that ownership structure of cooperatives is not always a decisive factor for their financial success. [EconLit citations: Q130, G320, C440].

This paper illustrates the power of modern statistical modelling in estimating measures of market risk, here applied to the Brent and WTI spot price of oil. Both Value-at-Risk (VaR) and Expected Shortfall (ES) are cast in terms of conditional centiles based upon semiparametric regression models. Using the GAMLSS statistical framework, we stress the important aspects of selecting a highly flexible parametric distribution (skewed Student's t distribution) and of modelling both skewness and kurtosis as nonparametric functions of the price of oil futures. Furthermore, an empirical application characterises the relationship between spot oil prices and oil futures - exploiting the futures market to explain the dynamics of the physical market. Our results suggest that NYMEX WTI has heavier tails compared with the ICE Brent. Contrary to the common platitude of the industry, we argue that 'somebody knows something' in the oil business.

This article provides evidence regarding the performance of momentum investment strategies that is consistent with the Neoclassical Theory. More specifically, while momentum investment returns appear orthogonal to systematic risk in the extant literature, this article illustrates that they are due to correlated changes of hedge portfolio systematic risk exposures with market conditions. Momentum portfolios are excellent market timers in both expanding and contracting markets. Their returns however are generally not abnormal when timing is considered in an augmented unconditional Capital Asset Pricing Model (CAPM), while the standard version erroneously considers them to be so, possibly explaining why momentum studies have so far rejected the Neoclassical Theory.

As the world economy highly depends on crude oil, it is important to understand the dynamics of crude oil production and export capacity of major oil-exporting countries. Since crude oil resources are predominately located in the OPEC Middle East, these countries are expected to have significant leverage in the world crude oil markets by taking into account a range of uncertainties. In this study, we develop a scenario for crude oil export and production using the ACEGES model considering uncertainties in the resource limits, demand growth, production growth, and peak/decline point. The results indicate that the country-specific peak of both crude oil export and production comes in the early this century in the OPEC Middle East countries. On the other hand, they occupy most of the world export and production before and after the peak points. Consequently, these countries are expected to be the key group in the world crude oil markets. We also find that the gap between the world crude oil demand and production broadens over time, meaning that the acceleration of the development of ultra-deep-water oil, oil sands, and extra-heavy oil will be required if the world continuous to heavily rely on oil products.

Multiattribute additive value functions constitute an important class of models for multicriteria decision making. Such models are often used to rank a set of alternatives or to classify them into pre-defined groups. Preference disaggregation techniques have been used to construct additive value models using linear programming techniques based on the assumption of monotonic preferences. This paper presents a methodology to construct non-monotonic value function models, using an evolutionary optimization approach. The methodology is implemented for the construction of multicriteria models that can be used to classify the alternatives in pre-defined groups, with an application to credit rating.

This paper reproduces the performance of a geometric average Spot Energy Index by investing only in a subset of stocks from the Dow Jones Composite Average, the FTSE 100 and Bovespa Composite indexes, and in two pools including only stocks of the energy sector from the US and the UK respectively. Daily data are used and the index-tracking problem for passive investment is addressed with two innovative evolutionary algorithms; the differential evolution algorithm and the genetic algorithm, respectively. The performance of the suggested investment strategy is tested under three different scenarios: buy-and-hold, quarterly, and monthly rebalancing;accounting for transaction costs where necessary.

Abstract 

The fusion of agent-based and geospatial models represents an exciting new synthesis for social science and economics. It has the potential to improve the theory and the practice of modelling complex real-world phenomena. Yet, to date, there has been little systematic analysis at the conceptual and logical levels of how to fuse agent-based and geospatial models for the representation and reasoning of socioeconomic phenomena. Here both sets of issues are explored. In particular, it will be argued that the development of synthetic models requires autonomous agents and flexible organisational structures that can complete their objectives while situated in a dynamic and uncertain geoenvironment represented by the concept of Elementary_geoParticle. As an example of the concept, I present a preliminary conceptual model of global energy to demonstrate the validity and possible uses of the proposed technique.