|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/machine-learning-algorithms-r-business-analytics
课程评论：没有评论
课程名称: 商业分析中的R语言机器学习算法 课程概述: 商业分析中最令人兴奋的方面之一是利用机器学习算法在数据中寻找模式。在本课程中，您将获得机器学习算法的重要性及其模型的概念基础，这些模型用于发现与商业问题相关的可行洞察。一些算法用于预测数值结果，其他算法则用于预测结果的分类。还有一些算法可用于从丰富的数据集中创建有意义的分组。完成本课程后，您将能够描述每种算法的适用场景。同时，您将有机会使用R和RStudio运行这些算法，并通过R笔记本有效地传达结果。 课程大纲: 1. **课程导向与模块一: 回归算法在商业数据分析中的应用** - 描述: 探索性数据分析（EDA）是商业分析工作流程中的关键一步，但EDA是一种耗时的方法来揭示复杂关系。此外，通常用于EDA的可视化方法并不适合量化结果的可靠性或进行预测。 2. **模块二: 机器学习框架与逻辑回归** - 描述: 理解商业中的机器学习及逻辑回归的基本概念。 3. **模块三: 分类算法** - 描述: 一般的分类算法，包括K最近邻（KNN）和决策树。 4. **模块四: 聚类算法** - 描述: 聚类算法，包括K均值和DBSCAN算法。
Name:Course Orientation and Module 1: Regression Algorithm for Testing and Predicting Business Data
Description:Exploratory data analysis (EDA) is a critical step in the business analytic workflow; however, EDA is a time-consuming approach for uncovering complex relationships. Moreover, the visualizations that are often used for EDA do not lend themselves well for quantifying confidence in results or for making predictions.
Name:Module 2: Framework for Machine Learning and Logistic Regression
Description:Gain an understanding of machine learning in business and logistic regression
Name:Module 3: Classification Algorithms
Description:Classification algorithms in general, K-nearest neighbors, and decision trees.
Name:Module 4: Clustering Algorithms
Description:Clustering algorithms, k-means, and DBSCAN
One of the most exciting aspects of business analytics is finding patterns in the data using machine learning algorithms. In this course you will gain a conceptual foundation for why machine learning algorithms are so important and how the resulting models from those algorithms are used to find actionable insight related to business problems. Some algorithms are used for predicting numeric outcomes, while others are used for predicting the classification of an outcome. Other algorithms are used for creating meaningful groups from a rich set of data. Upon completion of this course, you will be able to describe when each algorithm should be used. You will also be given the opportunity to use R and RStudio to run these algorithms and communicate the results using R notebooks.
