ARTÍCULO
TITULO

CREDIT SCORING WITH AN ENSEMBLE DEEP LEARNING CLASSIFICATION METHODS ? COMPARISON WITH TRADITIONAL METHODS

Ognjen Radovic    
Srdan Marinkovic    
Jelena Radojicic    

Resumen

Credit scoring attracts special attention of financial institutions. In recent years, deep learning methods have been particularly interesting. In this paper, we compare the performance of ensemble deep learning methods based on decision trees with the best traditional method, logistic regression, and the machine learning method benchmark, support vector machines. Each method tests several different algorithms. We use different performance indicators. The research focuses on standard datasets relevant for this type of classification, the Australian and German datasets. The best method, according to the MCC indicator, proves to be the ensemble method with boosted decision trees. Also, on average, ensemble methods prove to be more successful than SVM.

 Artículos similares

       
 
H. Ardiyanti, D. Puspitarum, O. F. Maryana, W. A. Pujakesuma     Pág. 197 - 200
This article reports the results synthesis of composite Fe3O4/SiO2 and nanoparticles from natural resources (sugarcane bagasse). The synthesis of Fe3O4 and SiO2 nanoparticles used co-precipitation and sol-gel methods with SiO2 from sugarcane bagasse as a... ver más

 
Katarina Njegic, Ines Djokic, Vesna Milanovic    
Research Question: This paper investigates whether the Narver and Slater?s market orientation scale (MKTOR scale) is reliable, valid and applicable in the Serbian exporters? context. Motivation: Previous studies that examined the applicability of the MKT... ver más
Revista: Management

 
Dragan Pamucar, Nikola Kne?evic, Dragana Macura, Boban Ðorovic    
Research Question: The paper explores the problem of defining the number of required employees and their skills, as well as optimizing the work time. Motivation: Motivation for this paper arises from the fact that an organizational structure of business ... ver más
Revista: Management

 
Gülsah Atagan, Aylin Kavak     Pág. 34 - 57
        If we looked at the oldest fraud and its history, it goes to until  the invention of money (about 750 th year B.C ).There is also certain range of fraud in the barter system. After merchandise commoditizati... ver más

 
Muji Listyo Widodo,Rinekso Soekmadi,Hadi Susilo Arifin     Pág. 55 - 61
Betung Kerihun National Park (BKNP) is a transboundary conservation area. BKNP region has various attractive ecotourism activities are covered in the context of the nature, culture and 55adventure. But the number of foreign tourists who have visited is s... ver más