摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-人工智能的新数据在一份新的报告中呈现。根据NewsRx记者在德国Y Garching的新闻报道，研究表明，“我们比较了线性回归、局部多项式回归和选定的机器学习方法来建模信用利差变化。使用部分依赖图(PDPs)和H-统计量，我们发现机器学习模型比回归模型的表现更好，主要归因于复杂的非线性，而不是相互作用。”新闻记者从慕尼黑技术大学（TU Munich）的研究中获得了一句话，“PDP还被用来执行一个因素hed ging。”应用shapleey可加性解释(SHAP)值对信用利差变化进行分解，并将该框架应用于美国和欧元区不同成熟度的企业和覆盖债券信用利差变化，量化了几个宏观经济和金融变量的影响。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on Artificial Intelligence are presented in a new report. According to news reporting from Garching, German y, by NewsRx journalists, research stated, “We compare linear regression, local polynomial regression and selected machine learning methods for modeling credit spread changes. Using partial dependence plots (PDPs) and H-statistic, we find t hat the outperformance of machine learning models compared to regression ones is mostly attributable to complex non-linearities and not to interactions.” The news correspondents obtained a quote from the research from Technical Univer sity Munich (TU Munich), “The PDPs are additionally used to perform a factor hed ging. For the first time, credit spread changes are decomposed by applying SHapl ey Additive exPlanation (SHAP) values. The proposed frame-work is applied to US a nd Euro Area corporate and covered bond credit spread changes of different matur ities to quantify the influence of several macroeconomic and financial variables .”
NETL
NSTL