Credit Scoring Model Based on Neural Network with Particle Swarm Optimization

Gao, Liang; Zhou, Chen; Gao, Hai-Bing; Shi, Yihui

doi:10.1007/11881070_11

Cited by 19 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some studies compared their proposed hybrid system with single nonlinear methods or with another type of hybrid systems. For example, [191] suggested a particle swarm optimization (SPSO) approach for training feedforward NNs for credit scoring. They applied successfully their method to real credit problems.…”

Section: Credit Evaluationmentioning

confidence: 99%

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

Bahrammirzaee

2010

Neural Comput & Applic

442

192

View full text Add to dashboard Cite

Nowadays, many current real financial applications have nonlinear and uncertain behaviors which change across the time. Therefore, the need to solve highly nonlinear, time variant problems has been growing rapidly. These problems along with other problems of traditional models caused growing interest in artificial intelligent techniques. In this paper, comparative research review of three famous artificial intelligence techniques, i.e., artificial neural networks, expert systems and hybrid intelligence systems, in financial market has been done. A financial market also has been categorized on three domains: credit evaluation, portfolio management and financial prediction and planning. For each technique, most famous and especially recent researches have been discussed in comparative aspect. Results show that accuracy of these artificial intelligent methods is superior to that of traditional statistical methods in dealing with financial problems, especially regarding nonlinear patterns. However, this outperformance is not absolute.

show abstract

Section: Credit Evaluationmentioning

confidence: 99%

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

Bahrammirzaee

2010

Neural Comput & Applic

442

192

View full text Add to dashboard Cite

show abstract

“…The feed-forward neural networks (NNs) trained by structure-tuning particle swarm optimization (SPSO) [19] is adopted to facilitate efficient service discovery. The flow of the training algorithm is discussed in Figure 7.…”

Section: Collaborative Services Platform and Publishing And Discovering Agentmentioning

confidence: 99%

Interoperability of Cross-organizational Workflows based on Process-view for Collaborative Product Development

Jiang

Shao

Qiu

et al. 2008

Concurrent Engineering

View full text Add to dashboard Cite

Collaborative product development (CPD) has been widely accepted as an advanced collaboration paradigm that combines geographically distributed product development teams to develop product collaboratively and efficiently. Interoperability of cross-organizational workflows is important for CPD to facilitate the successful execution of the whole product development process across enterprises boundaries. This article, describes a timed colored petri net (TCPN) and process-view combined approach to construct cross-organizational workflows, and a three models framework of `TCPN workflow models — Process-view workflow models — Integrated process-view workflow model' is proposed to realize the interoperability of cross-organizational workflows for CPD. A multi-agent system PVMAS provides a mediated architecture for distributed workflow management systems interoperability among cooperative enterprises. Under this architecture, a service discovery algorithm is provided for discovering the most suitable services enterprises need, a TCPN algebra model and a character string mapping algorithm are proposed to automate the mapping from a TCPN workflow model to a process-view workflow model, and the synchronization points are designated in the integrated process-view workflow model to coordinate the execution of cross-organizational workflow instances. Finally, a case study of the collaborative development of a motorcycle is presented to verify the validity of our approach for cross-organizational workflows interoperability in CPD.

show abstract

“…Em Gao et al (2006), a técnica PSO foi aplicada para ajustar simultaneamente a estrutura e os pesos das conexões de RNs. Os autores propuseram uma modificação no PSO, chamado de SPSO, para solucionar esse problema.…”

Section: Ajuste De Parâmetros De Rnsunclassified

“…Diversos trabalhos encontrados na literatura tratam do problema de ajuste de parâmetros para SVMs (Lorena & Carvalho, 2006;Huang & Wang, 2006;Souza & Carvalho, 2005;Souza et al, 2006;Imbault & Lebart, 2004;Zhang & Jiao, 2005;Acevedo et al, 2006) e para RNs (Castillo et al, 2007;Gao et al, 2006;Braun & Weisbrod, 1993;Dodd, 1990;Leung et al, 2003;Tsai et al, 2006). Muitos deles utilizam algoritmos bioinspirados para isso.…”

Section: Conclusãounclassified

Ajuste de parâmetros de técnicas de classificação por algoritmos bioinspirados

Rossi¹

View full text Add to dashboard Cite

Em primeiro lugar gostaria de agradecer a Deus, por estar sempre tão presente em minha vida. Ao meu orientador Prof. Dr. André Carvalho, pela orientação durante os dois anos de mestrado, pela ajuda nesta dissertação, por proporcionar as condições necessárias para o desenvolvimento deste trabalho, pela confiança depositada em mim, pelos momentos de positivismo e pela amizade. Ao Prof. Dr. Carlos Soares do LIAAD, Porto-Portugal, pela contribuição com este trabalho, pela recepção em Porto e pelo seu entusiasmo como pesquisador. Aos meus pais João e Maria Inês, pelo amor incondicional e pelo exemplo de honestidade e humildade. Aos meus irmãos Flávio, Regina e Ana Elisa, pelas brincadeiras e por estarem sempre prontos para ajudar. A minha namorada Joyce, pelo apoio, demonstrações de amor e pelo seu sorriso, que me faz tão bem. Aos meus familiares, que me apoiam desde a graduação. Aos amigos e professores do BIOCOMP e do LABIC, pelo acolhimento, pelos ensinamentos e também pelos momentos de descontração. Em especialà Ronaldo Cristiano Prati, pelos algoritmos dos testes estatísticos e pela ajuda com o L A T E X,à Ana Carolina Lorena, pela ajuda e correções do projeto que se tornaria este trabalho eà Bruno Feres de Souza, pelos conjuntos de dados e ensinamentos. Aos amigos com quem morei, mesmo que por pouco tempo, durante esses dois anos em São Carlos: Fábio, Vinícius e Régis, pelo incentivo e companheirismo. A todos os funcionários do ICMC da USP, pela competência e dedicação. A FAPESP e ao CNPq, pelo apoio financeiro para a realização deste estudo.

show abstract

Credit Scoring Model Based on Neural Network with Particle Swarm Optimization

Cited by 19 publications

References 5 publications

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

A comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems

Interoperability of Cross-organizational Workflows based on Process-view for Collaborative Product Development

Ajuste de parâmetros de técnicas de classificação por algoritmos bioinspirados

Contact Info

Product

Resources

About