在当今的大数据和人工智能时代,机器学习在企业财务预警领域应用是热门的话题,而XGBoost算法是最重要的机器学习方法之一。论文在回顾上市公司财务预警相关研究的基础上,由于传统统计方法、神经网络法、决策树和GBDT算法在财务预警方面...在当今的大数据和人工智能时代,机器学习在企业财务预警领域应用是热门的话题,而XGBoost算法是最重要的机器学习方法之一。论文在回顾上市公司财务预警相关研究的基础上,由于传统统计方法、神经网络法、决策树和GBDT算法在财务预警方面存在运行效率低、计算速度慢、学习效率低、缺乏交叉验证、过拟合、无自动筛选、预测精度低等方面的问题,提出基于机器学习的XGBoost算法建立了中国上市公司的财务预警模型。结果发现:XGBoost算法对中国上市公司的财务预警有较好的识别,具有广泛的适用性和推广价值。论文丰富了传统的公司财务预警方法,提供了公司财务预警的新思路。In today’s era of big data and artificial intelligence, the application of machine learning in the field of enterprise financial early warning is a hot topic, and the XGBoost algorithm is one of the most important machine learning methods. Based on a review of relevant research on financial distress prediction for listed companies, this paper proposes the establishment of a financial distress prediction model for Chinese listed companies using the XGBoost algorithm, which is rooted in machine learning. This proposal arises due to the shortcomings of traditional statistical methods, neural networks, decision trees, and the GBDT algorithm in financial distress prediction, such as low operational efficiency, slow computation speeds, poor learning efficiency, lack of cross-validation, overfitting, absence of automatic feature selection, and low prediction accuracy. The result shows that: XGBoost algorithm has a good identification of the financial warning of Chinese listed companies and has a wide applicability and promotion value. The paper enriches the traditional company financial warning method and provides the new idea of company financial warning.展开更多
以2014—2019年珲春地区红外相机拍摄的东北虎数据为基础,基于XGBoost算法构建了虎出没区域风险等级划分模型。由模型检验可知:模型的准确率为93.51%,精确率为93.85%,召回率为93.08%,F1值为93.31%,Cohen s Kappa统计系数为90.2%。研究...以2014—2019年珲春地区红外相机拍摄的东北虎数据为基础,基于XGBoost算法构建了虎出没区域风险等级划分模型。由模型检验可知:模型的准确率为93.51%,精确率为93.85%,召回率为93.08%,F1值为93.31%,Cohen s Kappa统计系数为90.2%。研究结果表明:基于XGBoost算法构建的人-虎共存区域风险等级划分模型分类效果好、预测准确度高,运用该模型对人-虎共存区域进行风险等级划分是可行的。展开更多
文摘在当今的大数据和人工智能时代,机器学习在企业财务预警领域应用是热门的话题,而XGBoost算法是最重要的机器学习方法之一。论文在回顾上市公司财务预警相关研究的基础上,由于传统统计方法、神经网络法、决策树和GBDT算法在财务预警方面存在运行效率低、计算速度慢、学习效率低、缺乏交叉验证、过拟合、无自动筛选、预测精度低等方面的问题,提出基于机器学习的XGBoost算法建立了中国上市公司的财务预警模型。结果发现:XGBoost算法对中国上市公司的财务预警有较好的识别,具有广泛的适用性和推广价值。论文丰富了传统的公司财务预警方法,提供了公司财务预警的新思路。In today’s era of big data and artificial intelligence, the application of machine learning in the field of enterprise financial early warning is a hot topic, and the XGBoost algorithm is one of the most important machine learning methods. Based on a review of relevant research on financial distress prediction for listed companies, this paper proposes the establishment of a financial distress prediction model for Chinese listed companies using the XGBoost algorithm, which is rooted in machine learning. This proposal arises due to the shortcomings of traditional statistical methods, neural networks, decision trees, and the GBDT algorithm in financial distress prediction, such as low operational efficiency, slow computation speeds, poor learning efficiency, lack of cross-validation, overfitting, absence of automatic feature selection, and low prediction accuracy. The result shows that: XGBoost algorithm has a good identification of the financial warning of Chinese listed companies and has a wide applicability and promotion value. The paper enriches the traditional company financial warning method and provides the new idea of company financial warning.
文摘以2014—2019年珲春地区红外相机拍摄的东北虎数据为基础,基于XGBoost算法构建了虎出没区域风险等级划分模型。由模型检验可知:模型的准确率为93.51%,精确率为93.85%,召回率为93.08%,F1值为93.31%,Cohen s Kappa统计系数为90.2%。研究结果表明:基于XGBoost算法构建的人-虎共存区域风险等级划分模型分类效果好、预测准确度高,运用该模型对人-虎共存区域进行风险等级划分是可行的。
