Applied Machine Learning & Inference in R

This unit introduces applied supervised and unsupervised modeling workflows in R, including decision trees, SVMs, neural networks, clustering, and model evaluation using Rattle and core R packages. It also develops applied statistical inference and visualization skills (t-tests, z-tests, variance testing, ggplot2) through hands-on projects that prepare learners for advanced model refinement and deployment in the final unit.

Learning Objectives

• Apply supervised learning methods (decision trees, support vector machines, neural networks) and clustering techniques in R and Rattle to train, validate, and interpret models on real datasets.
• Analyze and visualize data using ggplot2 and R summary functions to compute medians, frequencies, distributions, and other descriptive statistics that guide modeling choices.
• Demonstrate proficiency performing statistical inference in R—including t-tests, z-tests, and tests for equal variances—interpreting results, verifying assumptions, and documenting conclusions.
• Evaluate model performance and tuning strategies (e.g., pruning, parameter tuning, resampling) through project-based assessments and select appropriate approaches for further development or deployment.