Artificial neural networks with feature transformation based on domain knowledge for the prediction of stock index futures

A feature transformation method based on domain knowledge for arti?cial neural networks (ANNs) is proposed. The method of feature transformation based on domain knowledge converts continuous values into discrete values in accordance with the knowledge of experts in speci?c application domains. This approach effectively ?lters data, trains the classi?er, and extracts the rules from the classi?er. In addition, it reduces the dimensionality of the feature space, which not only decreases the cost and time in the operation but also enhances the generalizability of the classi?er. The experimental results of the proposed approach will be compared and tested statistically with the results of the linear transformation method. The results show that the method of feature transformation based on domain knowledge outperforms the linear transformation in modelling of ANNs. Copyright © 2004 John Wiley & Sons, Ltd.     

The service sector of Cuba: An analysis and critique

The Cuban economy has experienced a significant increase in foreign direct investment over the past decade due to the end of the Soviet Union and the establishment of more liberal trade policies. Although the U.S. embargo of trade with Cuba still exists, there has been movement lately that suggests the end of the four‐decades‐old policy. The purpose of this article is to analyze the current Cuban business environment and to identify potential entrepreneurial opportunities in the service sector. Major trade partners are also reviewed and managerial implications discussed. © 2006 Wiley Periodicals, Inc.     

Managing New Product Design and Development: an Anglo-German Study

This article reports the results of a study of innovation and product development at 245 manufacturing sites in the UK and Germany. It examines the relationship between design and performance and the competitiveness of the UK and Germany in design and manufacturing. Overall, few sites reached "world-class" standards - 9% in Germany and 3% in the UK, although many sites were not far below these standards.     

Adverse selection in group insurance: The virtues of failing to represent voters

Compared with non-union workers, union workers take more of their compensation in the form of insurance. This may be because unions choose democratically, and democratic choice mitigates adverse selection in group insurance. Relative to individually-purchased insurance, we show that group insurance chosen by an ideal profit-maximizing employer can be worse for every employee, while group insurance chosen democratically can be much better. The reason is that democracy can fail to represent the preferences of almost half the group.Received: January 2003, Accepted: September 2004, JEL Classification: J51, D82, G22     

This is what the leading indicators lead

We propose an optimal filter to transform the Conference Board Composite Leading Index (CLI) into recession probabilities in the US economy. We also analyse the CLI's accuracy at anticipating US output growth. We compare the predictive performance of linear, VAR extensions of smooth transition regression and switching regimes, probit, non‐parametric models and conclude that a combination of the switching regimes and non‐parametric forecasts is the best strategy at predicting both the NBER business cycle schedule and GDP growth. This confirms the usefulness of CLI, even in a real‐time analysis. Copyright © 2002 John Wiley & Sons, Ltd.     

Future information systems for road transport: A Delphi panel-derived scenario

Modern information and microelectronic technology can be used to improve road traffic. The aim of this study is to create scenarios on how new information systems for improved road traffic can evolve. What are the driving forces? Who can act? Who can benefit? What are the social impacts?Through the use of a Delphi panel of professionals, researchers, and informed generalists, we have gathered impulses for the scenarios on how information technology, communication means, and control systems can reshape future road traffic. The issue studied is how this “Road Transport Informatics” (RTI) will evolve.     

Linking Public Investment to Private Investment. The Case of Spanish Regions

Public investment constitutes one of the main instruments of regional policies. The existence of a direct link between infrastructure and regional income per capita is usually accepted. Literature also describes a positive effect of public investment on private capital accumulation. This paper seeks to provide new empirical evidence on this latter relationship for the case of Spanish regions over the period 1965–1997 using panel data methodology. The results show a positive effect of productive and social public investment (especially in education) on private investment. The spillover effects generated by the productive infrastructures located in other regions do not seem to encourage the private investment in neighbouring regions. Public consumption and interest rate exert a negative influence on private capital accumulation. These results are robust to changes in the econometric specification.     

Strategic trading and learning about liquidity

Many practitioners point out that the speculative profits of institutional traders are eroded by the difficulty in gauging the price impact of their trades. In this paper, we develop a model of strategic trading where speculators face such a dilemma because of incomplete information about time-varying market liquidity. Unlike the competitive market makers that they trade against, informed traders do not know the distribution of liquidity (“noise”) trades. Instead, they have to learn about liquidity from past prices and trading volume. This learning implies that strategic trades and market statistics such as informational efficiency are path-dependent on past market outcomes. Our paper also has normative implications for practitioners.