BUS-K 353 Business Analytics and Modeling
This course focuses on the process of transforming data into insights for solving real world business problems. It takes a layered approach in generating insights: first, descriptive analytics employs visual analytics to characterize data; second, prescriptive analytics focuses on the optimal strategies that “should” be undertaken in the future; third, predictive analytics centers on the use of machine learning algorithms to identify the likelihood of future outcomes based on historical data and to find patterns of relationships between data elements in large and noisy datasets. Topics include: data exploration, data preparation, nonlinear optimization, Monte Carlo simulation, parametric (e.g., linear regression, logistic regression) and non-parametric (e.g., classification trees, regression trees) supervised machine learning techniques, and unsupervised machine learning techniques (e.g., cluster analysis). Through extensive demonstrations and hands-on exercises, using a popular programming language (e.g., R), students get systematic training in data cleaning, training models, interpreting the findings, and performing optimization analysis.