In this paper, a problem set activity focused on understanding and applying unsupervised and supervised chemometric methods for the analysis of biodiesel-diesel blended fuels is described. This problem set was utilized in two upper-level analytical elective courses aimed for junior and senior level students. The data set consists of peak areas taken from gas chromatograms comprising various biodiesel concentrations and feedstock types. Students are tasked with analyzing the data set using principal component analysis (PCA), hierarchical cluster analysis (HCA), and k-nearest neighbors (kNN). The primary purpose of this problem set is to gain hands-on experience manipulating and drawing conclusions about large data sets using chemometric methods. The problem set activity utilizes a large GCMS data set with many varieties of sample types and can be included at any institution with no need for a GCMS instrument on campus.