Data Science via Machine Learning and Statistical Modeling

Philosophy of modeling and learning using data. Prediction using linear, polynomial, interaction regressions and machine learning including neural nets and random forests. Probability estimation with asymmetric cost classification. Underfitting vs. overfitting and R-squared. Model validation. Correlation vs. causation. Interpretations of linear model coefficients. Formal instruction of statistical computing. Data manipulation and visualization using modern libraries. Writing Intensive. Recommended corequisites include ECON 382, MATH 341, MATH 369 or their equivalents.

034233