High-performance bankruptcy prediction model using Graphics Processing Units

Ribeiro, Bernardete; Lopes, Noel; Silva, Catarina

http://hdl.handle.net/10400.8/14688

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
High-performance bankruptcy prediction model using Graphics Processing Units.pdf	In recent years the the potential and programmability of Graphics Processing Units (GPU) has raised a note-worthy interest in the research community for applications that demand high-computational power. In particular, in financial applications containing thousands of high-dimensional samples, machine learning techniques such as neural networks are often used. One of their main limitations is that the learning phase can be extremely consuming due to the long training times required which constitute a hard bottleneck for their use in practice. Thus their implementation in graphics hardware is highly desirable as a way to speed up the training process. In this paper we present a bankruptcy prediction model based on the parallel implementation of the Multiple BackPropagation (MBP) algorithm which is tested on a real data set of French companies (healthy and bankrupt). Results by running the MBP algorithm in a sequential processing CPU version and in a parallel GPU implementation show reduced computational costs with respect to the latter while yielding very competitive performance.	127.64 KB	Adobe PDF	Download

Send Feedback

Authors

Ribeiro, Bernardete

Lopes, Noel

Silva, Catarina

Abstract(s)

In recent years the the potential and programmability of Graphics Processing Units (GPU) has raised a note-worthy interest in the research community for applications that demand high-computational power. In particular, in financial applications containing thousands of high-dimensional samples, machine learning techniques such as neural networks are often used. One of their main limitations is that the learning phase can be extremely consuming due to the long training times required which constitute a hard bottleneck for their use in practice. Thus their implementation in graphics hardware is highly desirable as a way to speed up the training process. In this paper we present a bankruptcy prediction model based on the parallel implementation of the Multiple BackPropagation (MBP) algorithm which is tested on a real data set of French companies (healthy and bankrupt). Results by running the MBP algorithm in a sequential processing CPU version and in a parallel GPU implementation show reduced computational costs with respect to the latter while yielding very competitive performance.

Description

EISBN - 978-1-4244-6918-5
Conference name - 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010; Conference date - 18 July 2010 - 23 July 2010; Conference code - 85188
Fonte: https://www.researchgate.net/publication/224181340_IJCNN_High-Performance_Bankruptcy_Prediction_Model_using_Graphics_Processing_Units

Keywords

Graphics processing unit Neurons Predictive models Computational modeling Artificial neural networks Training Companies

URI

http://hdl.handle.net/10400.8/14688

Citation

B. Ribeiro, N. Lopes and C. Silva, "High-performance bankruptcy prediction model using Graphics Processing Units," The 2010 International Joint Conference on Neural Networks (IJCNN), Barcelona, Spain, 2010, pp. 1-7, doi: https://doi.org/10.1109/IJCNN.2010.5596711.