Il libro è attualmente esaurito

Credit Risk Analytics: Predictive Modeling Techniques Comparison

Automated comparison of various predictive modeling techniques on credit card data

Autori

Ravinder Singh

Parametri

Pagine: 156pagine
Tempo di lettura: 6ore

Economia e affari

Maggiori informazioni sul libro

The book delves into the critical role of credit scoring in financial institutions, evaluating both traditional statistical methods and modern machine learning techniques. It highlights the importance of predictive modeling for assessing defaulter risk and addresses the lack of comprehensive studies comparing various tools. A macro is designed to enhance transparency in credit scoring, utilizing Dtreg and SAS Enterprise Miner for analysis. Findings indicate that support vector machines and genetic programming excel in classifying loan applicants, emphasizing the significance of cross-validation in these assessments.

Acquisto del libro

Credit Risk Analytics: Predictive Modeling Techniques Comparison, Ravinder Singh

Lingua
Pubblicato: 2012
product-detail.submit-box.info.binding: (In brossura)

Ti avviseremo via email non appena lo rintracceremo.

Metodi di pagamento

Ancora nessuna valutazione.Aggiungi una valutazione

Suggerisci una correzione

Titolo: Credit Risk Analytics: Predictive Modeling Techniques Comparison
Sottotitolo: Automated comparison of various predictive modeling techniques on credit card data
Lingua: Inglese
Autori: Ravinder Singh
Editore: LAP LAMBERT Academic Publishing
Pubblicato: 2012
Formato: In brossura
Pagine: 156
ISBN13: 9783659300868
Tag: Economia e affari
Descrizione: The book delves into the critical role of credit scoring in financial institutions, evaluating both traditional statistical methods and modern machine learning techniques. It highlights the importance of predictive modeling for assessing defaulter risk and addresses the lack of comprehensive studies comparing various tools. A macro is designed to enhance transparency in credit scoring, utilizing Dtreg and SAS Enterprise Miner for analysis. Findings indicate that support vector machines and genetic programming excel in classifying loan applicants, emphasizing the significance of cross-validation in these assessments.