|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/credit-risk-modeling-using-sas/
课程评论：没有评论
**课程总结：使用SAS进行信用风险建模** 本课程深入讲解了银行如何利用SAS软件构建信用风险评分卡，以预测客户的违约概率。课程将引导学员从零开始，一步步掌握整个模型构建过程，包括数据准备、评分卡开发、模型稳健性检验、以及模型验证和准确性评估。 **核心内容涵盖：** * **数据集与变量理解：** 识别评分卡构建的关键变量。 * **数据处理与预处理：** 学习开发样本排除、观测窗口和表现窗口的设置。 * **模型设计与分析：** 掌握模型设计参数、年份分析（Vintage Analysis）和逾期率分析（Roll Rate Analysis）。 * **数据准备技术：** 涵盖缺失值和异常值的识别与处理。 * **数据集划分：** 学习如何分割训练集和测试集。 * **变量转换与评估：** 详细讲解分组（Fine and Coarse Classing）、信息值（Information Value）和证据权重（WOE）的应用。 * **模型诊断：** 理解并处理多重共线性问题。 * **逻辑回归模型构建：** 学习使用逻辑回归进行建模，并进行统计解释。 * **模型评估指标：** 掌握一致性（Concordance）、不一致性（Discordance）、Somer's D、C统计量、排序（Rank Ordering）、KS统计量和基尼系数（Gini Coefficient）等指标。 * **模型稳健性检验：** 学习检查聚类（Clustering）和拟合优度检验（Goodness of fit test）。 * **模型验证与准确性：** 重点讲解模型验证方法和Brier Score在模型准确性评估中的应用。 整门课程提供详细的SAS代码示例、输出解读和最佳实践建议，旨在帮助学员全面掌握使用SAS进行信用风险建模的技能。
Credit Risk Modeling is a technique used by lenders to determine the level of credit risk associated with extending credit to a borrower. In other words, it's a tool to understand the credit risk of a borrower. This is especially important because this credit risk profile keeps changing with time and circumstances. Credit risk modeling is the process of using statistical techniques and machine learning to assess this risk. The models use past data and various other factors to predict the probability of default and inform credit decisions.This course teaches you how banks use statistical modeling in SAS to prepare credit risk scorecard which will assist them to predict the likelihood of default of a customer. We will deep dive into the entire model building process which includes data preparation, scorecard development and checking for a robust model, model validation and checking for the accuracy of the model step by step from scratch. This course covers the following in detail with output interpretation, best practices and SAS Codes explanations:1) Understanding the dataset and the key variables used for scorecard building2) Development sample exclusions3) Observation and Performance window4) Model Design Parameters5) Vintage and Roll Rate Analysis6) Data Preparation which includes missing values and outlier identification and treatment7) Bifurcating Training and Test datasets 8) Understanding the dataset in terms of key variables and data structure9) Fine and Coarse classing10) Information value and WOE11) Multicollinearity 12) Logistic Regression Model development with statistical interpretation13) Concordance, Discordance, Somer's D and C Statistics14) Rank Ordering, KS Statistics and Gini Coefficient15) Checking for Clustering16) Goodness of fit test17) Model Validation and18) Brier Score for model accuracy
