Expected credit loss impairment: early recognition vs. income volatility

一项新的会计准则，即所谓的国际财务报告准则（IFRS），要求银行**以前瞻性的方式确认预期的信贷损失。实施IFRS 9的一种方法是基于**在管理监管资本的背景下使用的杠杆模型。这种方式尤其适用于CWB**金融集团，该集团目前正在转变其管理监管资本的方式。然而，IFRS 9**要求根据贷款的信用风险自初始确认以来是否显著增加**，对贷款进行不同的处理。因此，IFRS 9的实施需要一个定义和衡量什么构成信用风险的显著增加。寻找一种合适的统计方法来识别信用风险显著增加的贷款是本课题的主题。虽然信用风险应该及早认识到**，但对显著增长的定义过于宽泛会导致收入波动和信用风险估计过高。利用应用统计学和时间序列分析的方法，本项目的目标是找到一个合适的分类，将信用风险的早期识别与收入波动之间的权衡考虑在内。

A new accounting principle, the so-called International Financial Reporting Standard (IFRS) 9, requires banks**to recognize expected credit losses in a forward-looking way. One way of implementing IFRS 9 is based on**leveraging models used in the context of managing regulatory capital. This way applies particularly to CWB**Financial Group, which is currently transitioning its approach of managing regulatory capital. However, IFRS 9**asks for different treatments of loans depending on whether or not their credit risk has significantly increased**since initial recognition. Therefore, the implementation of IFRS 9 needs a definition and measuring of what**constitutes a significant increase in credit risk. Finding a suitable statistical way to identify loans with**significantly increased credit risk is the topic of this proposed project. While credit risk should be recognized**early, defining a significant increase too widely leads to income volatility and too high estimations of credit**risk. Using methods from applied statistics and time series analysis, the goal of this project is to find a suitable**classification that takes the trade-off between early recognition of credit risk and income volatility into**consideration.