|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/credit-risk-modelling-credit-scoring-with-machine-learning/
课程评论：没有评论
课程名称：信用风险建模与信用评分的机器学习 课程概述：欢迎参加《信用风险建模与信用评分的机器学习》课程。本课程是一个综合性项目课程，您将逐步学习如何使用逻辑回归、随机森林和K最近邻算法建立信用风险评估和信用评分模型。课程完美结合了机器学习和信用风险分析的知识，是提升数据科学技能和风险管理技术知识的理想机会。本课程将主要集中在三个方面：首先是数据分析，您将从多个角度探索信用数据集；第二是预测建模，您将学习如何使用机器学习构建信用风险评估和信用评分系统；第三是模型的准确性和性能评估。 在课程的介绍部分，您将了解信用风险分析的基本概念，包括其在银行和金融行业的应用案例，所使用的机器学习模型，以及信用风险建模中的技术挑战和局限性。接下来，您将深入学习信用风险评估模型的工作原理，包括数据收集、数据预处理、特征选择、数据划分、模型选择、模型训练、信用风险评估、信用评分、模型评估和模型部署等环节。 您还将学习影响信用评分的多个因素，例如支付历史、信用利用率、信用历史的长度、未偿还债务、信用组合以及新信用询问等因素。掌握所有必要的信用风险分析知识后，我们将开始项目。首先，您将逐步学习如何设置Google Colab IDE，并学习如何从Kaggle下载信用数据集。一切准备就绪后，您将进入项目的第一个部分，探索信用数据集的各个方面，进行数据可视化并识别模式。 在第二部分，您将逐步学习如何使用逻辑回归、随机森林和K最近邻算法构建信用风险评估模型和信用评分系统。同时，在第三部分，您将学习使用交叉验证、精确率和召回率等多种方法评估模型的准确性和性能。最后，在课程结束时，我们将使用Gradio部署该机器学习模型，并进行测试以确保模型正常运行并产生准确结果。 在学习此课程之前，我们应当思考：为什么要构建信用风险评估模型和信用评分系统？答案在于，准确的信用风险评估和评分是银行和金融机构在复杂的金融生态系统中作出明智放贷决策的关键。通过利用机器学习算法和数据驱动的洞察力，我们可以提高决策的准确性，有效降低信用风险，并优化放贷实践。此外，掌握构建复杂信用风险模型和评分系统的技能，可以在金融科技行业创造更多的职业机会。 在本课程中，您将学到以下内容： - 信用风险分析的基本基础，信用风险建模的技术挑战和局限性，以及其在银行和金融行业的应用案例。 - 信用风险评估模型的工作原理，包括数据收集、预处理、特征选择、模型选择和训练等。 - 影响信用评分的因素，如支付历史、信用利用率等。 - 如何从Kaggle寻找和下载信用数据集。 - 数据清理技巧，包括去除缺失值和重复值。 - 分析债务收入比与违约率之间的相关性。 - 使用逻辑回归、随机森林和K最近邻算法构建信用风险评估模型。 - 使用决策树回归器预测信用评分。 - 使用Gradio部署机器学习模型。 - 使用精确率、召回率和交叉验证评估模型的准确性和性能。
Welcome to Credit Risk Modelling & Credit Scoring with Machine Learning course. This is a comprehensive project based course where you will learn step by step on how to build a credit risk assessment and credit scoring model using logistic regression, random forest, and K Nearest Neighbors. This course is a perfect combination between machine learning and credit risk analysis, making it an ideal opportunity to level up your data science skills while improving your technical knowledge in risk management. The course will be mainly concentrating on three major aspects, the first one is data analysis where you will explore the credit dataset from multiple angles, the second one is predictive modeling where you will learn how to build credit risk assessment and credit scoring system using machine learning, and the third one is to evaluate the accuracy and performance of the model. In the introduction session, you will learn the basic fundamentals of credit risk analysis, such as getting to know its use cases in banking and financial industries, getting to know more about machine learning models that will be used, and you will also learn about technical challenges and limitations in credit risk modeling. Then, in the next section, you will learn how credit risk assessment model works.This section will cover data collection, data preprocessing, feature selection, splitting the data into training and testing sets, model selection, model training, assessing credit risk, assigning credit score, model evaluation, and model deployment. Afterward, you will also learn about several factors that contribute to credit score, for example like payment history, credit utilization ratio, length of credit history, outstanding debt, credit mix, and new credit inquiries. After you have learnt all necessary knowledge about credit risk analysis, we will start the project. Firstly you will be guided step by step on how to set up Google Colab IDE. In addition to that, you will also learn how to find and download credit dataset from Kaggle. Once everything is all set, we will enter the first project section where you will explore the credit dataset from various angles, not only that, you will also visualize the data and try to identify the patterns. In the second part, you will learn step by step on how to build credit risk assessment models and credit scoring systems using logistic regression, random forest, and K Nearest Neighbour. Meanwhile, in the third part, you will learn how to evaluate the accuracy and performance of the model using several methods like cross validation, precision, and recall. Lastly, at the end of the course, we will deploy this machine learning model using Gradio and we will conduct testing to make sure that the model has been fully functioning and produces accurate results.First of all, before getting into the course, we need to ask ourselves this question: why should we build a credit risk assessment model and credit scoring system? Well, here is my answer. In today's financial ecosystem, accurate credit risk assessment and scoring are essential for banks and financial institutions to make informed lending decisions. With the increasing complexity of financial markets and customer behavior, traditional methods alone may not suffice. By utilizing the power of machine learning algorithms and data-driven insights, we can enhance decision-making accuracy, mitigate credit risks effectively, and optimize lending practices. Moreover, mastering the skills in building sophisticated credit risk models and scoring systems can potentially lead to numerous career opportunities in financial technology sectors.Below are things that you can expect to learn from this course:Learn the basic fundamentals of credit risk analysis, technical challenges and limitations in credit risk modeling, and credit risk assessment use cases in banking and financial industriesLearn how credit risk assessment models work. This section will cover data collection, preprocessing, feature selection, train test split, model selection, model training. assessing credit risk and score, model evaluation, and model deploymentLearn about factors that affect credit score, such as payment history, credit utilization ratio, length of credit history, outstanding debt, credit mix, and new credit inquiriesLearn how to find and download credit dataset from KaggleLearn how to clean dataset by removing missing values and duplicatesLearn how to find correlation between debt to income ratio and default rateLearn how to analyze relationship between loan intent, loan amount, and default rateLearn how to build credit risk assessment model using logistic regressionLearn how to build credit risk assessment model using random forestLearn how to build credit risk assessment model using K Nearest NeighborLearn how to analyze relationship between outstanding debt and credit scoreLearn how to predict credit score using decision tree regressorLearn how to deploy machine learning model using GradioLearn how to evaluate the accuracy and performance of the model using precision, recall, and cross validation
