Machine Learning
本课程系统介绍机器学习算法及其商业应用。内容涵盖监督学习（线性回归、逻辑回归、决策树、随机森林、SVM、KNN）、无监督学习（K-Means聚类、层次聚类、主成分分析）、模型评估与选择、交叉验证、特征工程、过拟合与正则化等。课程使用scikit-learn库进行实践，结合客户分群、信用评分、推荐系统、销量预测等商业场景，培养学生运用机器学习解决实际商业问题的能力。
This course systematically introduces machine learning algorithms and their business applications. Topics include supervised learning (linear regression, logistic regression, decision trees, random forests, SVM, KNN), unsupervised learning (K-Means, hierarchical clustering, PCA), model evaluation and selection, cross-validation, feature engineering, overfitting, and regularization. Using scikit-learn with business scenarios like customer segmentation, credit scoring, recommendation systems, and sales forecasting, students develop skills to solve real business problems with machine learning.
基于电商平台客户交易行为数据，进行数据预处理和特征工程，使用K-Means聚类算法对客户进行分群，识别高价值客户、潜力客户、流失客户等不同群体的行为特征。建立分类预测模型，预测客户的购买意愿和价值等级。对比不同算法的预测效果，选择最优模型。最终提交包含客户画像、分群策略、营销建议的完整分析报告及Python代码。
Preprocess e-commerce customer transaction data and perform feature engineering. Apply K-Means clustering to segment customers into groups such as high-value, potential, and churned customers, identifying behavioral characteristics. Build classification models to predict purchase intent and customer value tiers. Compare algorithm performance and select the optimal model. Submit a complete report with customer personas, segmentation strategies, marketing recommendations, and Python code.