A Novel Soft Ensemble Model for Financial Distress Prediction with Different Sample Sizes

Wei Xu, Hongyong Fu and Yuchen Pan

Mathematical Problems in Engineering, 2019, vol. 2019, 1-12

Abstract:

This work presents a novel soft ensemble model (ANSEM) for financial distress prediction with different sample sizes. It integrates qualitative classifiers (expert system method, ES) and quantitative classifiers (convolutional neural network, CNN) based on the uni-int decision making method of soft set theory (UI). We introduce internet searches indices as new variables for financial distress prediction. By constructing a soft set representation of each classifier and then using the optimal decision on soft sets to identify the financial status of firms, ANSEM inherits advantages of ES, CNN, and UI. Empirical experiments with the real data set of Chinese listed firms demonstrate that the proposed ANSEM has superior predicting performance for financial distress on accuracy and stability with different sample sizes. Further discussions also show that internet searches indices can offer additional information to improve predicting performance.

Date: 2019
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://downloads.hindawi.com/journals/MPE/2019/3085247.pdf (application/pdf)
http://downloads.hindawi.com/journals/MPE/2019/3085247.xml (text/xml)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hin:jnlmpe:3085247

DOI: 10.1155/2019/3085247

Access Statistics for this article

More articles in Mathematical Problems in Engineering from Hindawi
Bibliographic data for series maintained by Mohamed Abdelhakeem ().