Scholarlink

Abstract <p>A classification of credit institutions using trees and decision forests to identify high-risk objects is considered. The CART decision tree models and Random Forest, Adaboost, and Xgboost decision forests have been developed enabling identification of high-risk credit institutions. Two computing systems, the Google Colaboratory cloud service (Google Colab) and the HybriLIT heterogeneous platform, were used for the calculations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Decision Trees and Forests in Classification of Credit Institutions

  • 期刊论文

  • 发表日期：

    2025年2月1日

查看全文
  • E. P. Akishina,
  • V. V. Ivanov,
  • A. S. Prikazchikova

摘要

Abstract

A classification of credit institutions using trees and decision forests to identify high-risk objects is considered. The CART decision tree models and Random Forest, Adaboost, and Xgboost decision forests have been developed enabling identification of high-risk credit institutions. Two computing systems, the Google Colaboratory cloud service (Google Colab) and the HybriLIT heterogeneous platform, were used for the calculations.