Several models in econometrics and finance have been proven to be computationally intractable due to their complexity. In this dissertation, we propose an evolutionary-genetic-algorithm for solving these types of problems. We extend the models so that less restrictive assumptions are required and we cope with the increased complexity by using a modified version of the evolutionary algorithm proposed for the simpler cases. More specifically, we study closer the estimation of switching regression models as introduced by Quandt (1958). The applicability of the proposed algorithms is examined through disequilibrium models; models that provide supply and demand functions for markets, when the price is not adjusted so that the quantity supplied equals the quantity demanded. We focus on the computational aspect of the deterministic switching regression models and we suggest a self-evolving genetic algorithm for solving these types of problems. As an illustration, we present results from Monte Carlo simulations and thereafter we apply the algorithm to the disequilibrium model proposed for the gasoline market during the “energy crisis”. We further extend the “general model” for markets in disequilibrium by incorporating dynamic relationships, and we examine the applicability of the proposed genetic algorithm in this more complex and realistic problem. Subsequently, the proposed genetic algorithm for the markets in disequilibrium is applied to financial models, where the structure and computational complexity are comparable with those of the switching regression models. As example, we apply the algorithm to minimizing portfolio tracking error with respect to a pre-specified index. The proposed genetic algorithm possesses unique characteristics that maximize the fitness of the algorithm itself for each individual problem. This is achieved through a Self-Evolving process that teaches the genetic algorithm what internal parameters improve the algorithm's fitness.

Thesis (M.S.)--Worcester Polytechnic Institute. / Keywords: comprehensiblity; technical analysis; genetic programming; overfitting; cooperative coevolution. Includes bibliographical references (p. 82-87).

Dissertation, Universität zu Köln, 2009. / Business and Economics (German Language) (Springer-11775) (GWV).

Dissertation, Universität zu Köln, 2009. / Business and Economics (German Language) (Springer-11775) (GWV).

Diss. Universität Duisburg-Essen, 2008. / Business and Economics (German Language) (Springer-11775) (GWV).

Diss. Universität Duisburg-Essen, 2008. / Business and Economics (German Language) (Springer-11775) (GWV).

This study examines the criteria which help academics receive National Institute of Health funds (NIH). The study covers 3,092 NIH recipients and non-recipients in the same department or institute at twenty-four universities. The universities are drawn from those below the top twenty in terms of receipt of NIH funds. With regards to performance, non- recipients have lower performance than recipients. A key determinant of the receipt of NIH funds is individual performance, as measured by the number of articles published and average citations per article in the two years immediately prior to the grant application. Professors receive more NIH money than do associates and assistant professors. Other positive contributors are the field of study, whether the academic has both a PhD. and Medical degree, and has licensed an innovation, been involved in the start of a new business and patented an invention through the university. To the extent that individual performance criteria represent the quality of the research proposal, allocation of NIH funds is based on merit. A Tobit model indicates that being highly cited does not guarantee increasing returns. Likewise, career citations have only a small statistically significant impact. In addition, a negative coefficient associated with the second derivatives of both articles published in 2006-07 and their associated citations indicate diminishing marginal returns.

Submitted by Elba Lopes (elba.lopes@fecap.br) on 2016-01-27T20:23:23Z No. of bitstreams: 2 Andrea_Galvao_Rodrigues1.pdf: 7473371 bytes, checksum: 178fd1f85ec7f498bb8b518b4571be6d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2016-01-27T20:23:23Z (GMT). No. of bitstreams: 2 Andrea_Galvao_Rodrigues1.pdf: 7473371 bytes, checksum: 178fd1f85ec7f498bb8b518b4571be6d (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2014-08-29 / The aim of this research was to identify, from the point of view of the knowledge building theory, the most important authors and institutions involved in finance research publications, from 1979 to 2012, to follow how the knowledge was built in this area. It was made a sociometric study of descriptive character, involving 223 articles from 78 journals. For this, the articles were divided in six thematic areas - Portfolio Theory, Capital Structure and Dividend Policy, CAPM, Market Efficiency, Price Options and Behavior Finance. Moreover, it was made the presentation of the cooperation social networks, splitting authors and institutions according to the thematic areas. Subsequently, it was made the analysis of the areas and institutions that most represent the publications in the searched population, as well as how the building of this knowledge occurred, based on the concepts of normal science and Thomas Kuhn paradigm. The following results were obtained, mapped and followed by the social network analysis (SNA): a) the theories that compose the Modern Finance Theory have their constitution anomalous concerning the paradigms; b) in the normal course of science, response to crisis was through new finance and its behavior model; c) the results presented between the dichotomy full and limited rationality in finance fit in the concept of normal science, according to its building course; d) Finance is a research area that has already presented its scientific paradigm; e) the comparison between the periods of published research and the knowledge building, in various moments, occurs through pre-paradigmatic periods, and its first divergence point was defined based on the real behavior factor. The answer was the insurgence and the insertion of behavior models in agents' decisions, which appeared in publications only in the last two decades, even under questionings of the dominant paradigm. / Nesta pesquisa, o objetivo foi identificar, sob a perspectiva da teoria de constru????o do conhecimento, os autores e as institui????es de destaque envolvidos na ??rea de publica????o da pesquisa em finan??as, entre 1979 e 2012, para acompanhar como ocorreu a constru????o do conhecimento nessa ??rea. Foi feito um estudo sociom??trico de car??ter descritivo, com 223 artigos, oriundos de 78 peri??dicos. Para tanto, os artigos foram divididos em seis ??reas tem??ticas - Teoria do Portfolio, Estrutura de Capital e Pol??tica de Dividendos, CAPM, Efici??ncia de Mercado, Precifica????o de Op????es e Finan??as Comportamentais - e foi feita a apresenta????o das redes sociais de coopera????o, dividindo autores e institui????es em conformidade com as ??reas tem??ticas. Posteriormente, procedeu-se ?? analise das ??reas e institui????es que mais representaram publica????es na popula????o pesquisada, e como ocorreu a constru????o desse conhecimento, a partir dos conceitos de ci??ncia normal e do paradigma de Thomas Kuhn. Foram obtidos os seguintes resultados, mapeados e acompanhados pela an??lise de rede social (ARS): a) as teorias componentes da MTF t??m sua constitui????o an??mala com rela????o aos paradigmas; b) na rota normal da ci??ncia, a resposta ?? crise foi por meio das novas finan??as e de seu modelo comportamental; c) os resultados entre a dicotomia da racionalidade plena e a limitada nas finan??as apresentaram-se e se encaixam no conceito de ci??ncia normal, de acordo com sua rota de constru????o; d) Finan??as foi uma ??rea de pesquisa a qual j?? apresentou seu paradigma cient??fico; e) a compara????o entre os per??odos da pesquisa publicada e a constru????o do conhecimento passa em diversos momentos por per??odos pr??-paradigm??ticos, e tem seu primeiro ponto de diverg??ncia definido com o fator comportamental comprovado; a resposta foi o surgimento e a inser????o dos modelos comportamentais nas decis??es dos agentes, que surgiu nas publica????es somente nas ??ltimas duas d??cadas, mesmo sob questionamentos do paradigma dominante.