Supply chain is a network of entire of the organizations, individuals, activities, technologies, and resources intricated in the formation and sale of a product. Thus, supply chain involves a huge amount of data. In ever-changing and today’s complex world, finding the relevant and appropriate data supplanted by the too much data that is available for the supply chain, is a big concern. Various methods have been proposed to analyze the supply chain. The present chapter deals with the analysis of complex supply chain data using machine learning. The goal was to gain customer insights from the dataset available on Kaggle. The data was preprocessed by eliminating null values and irrelevant features. Then classification and regression models, such as logistic regression, Gaussian Naïve Bayes, support vector machine (SVM), K-nearest neighbor (KNN), random forest, and decision trees, were utilized. These models helped in classification of late deliveries and fraudulent transactions, as well as in prediction of sales and order quantities. RFM analysis has been employed to segment customers based on recency, frequency, and monetary values. The data was visualized through graphs, comparing metrics like total sales and average price. Also, the chapter features a website displaying data preprocessing, feature plots, and classifier graphs.