Learn Differently by Mastering Business Analytics

This course prepares students with the data engineering knowledge required to complete data science research and navigate industry products.

This course demonstrates how to merge economic data analysis and applied econometric tools with the most common machine learning techniques, supporting the increasing need to understand “big data” due to the rapid advancement of computational methods. The course provides hands-on experience with the terminology, technology, and methodologies behind machine learning, with economic applications in marketing, finance, healthcare, and other areas. Primary topics include advanced regression techniques, resampling methods, model selection and regularization, classification models (logistic regression, Naive Bayes, discriminant analysis, k-nearest neighbors, neural networks), tree-based methods, support vector machines, and unsupervised learning (principal components analysis and clustering). Students apply both supervised and unsupervised machine learning techniques to solve economics-related problems with real-world datasets. No prior experience with R or Python is necessary.

This course teaches students advanced AI algorithms, addressing neural networks, deep learning architectures, and reinforcement learning. The course provides a high-level theoretical overview of each section and discusses practical applications through hands-on projects. The course uses Python as the programming language. The course prerequisites are: data analysis and feature engineering, traditional machine learning theory and practice, Python programming (intermediate level—e.g., familiarity with sci-kit learn, Matplotlib, NumPy, pandas), linear algebra, and first-order derivatives.

This survey course addresses governance frameworks and the algorithm techniques used to make decisions within an organization or in servicing clients. The recent acceleration in the use of artificial intelligence (AI)—and specifically machine learning (ML) techniques—has introduced unique opportunities and risks that require governance to ensure responsible and ethical use. The course begins by examining the intent of governance, its roots, and its current manifestations and goes on to explore trends that are shaping algorithmic decision-making in U.S. for-profit firms. Industries covered often include finance, healthcare, manufacturing, defense, and biotech.

This course focuses on the application of statistical tools used in estimating economic relationships. The course begins with a discussion of the linear regression model and an examination of the common problems encountered when applying this approach, including serial correlation, heteroscedasticity, and multicollinearity. Models with lagged variables are considered, as is estimation with instrumental variables, two-stage least squares, models with limited dependent variables, and basic time-series techniques.

This course prepares students to develop product solutions that deliver user value and provide viability for businesses in technology that use machine learning.

This course exposes students to the most popular forecasting techniques used across industries. We cover time series data manipulation and feature creation, including working with transactional and hierarchical time series data, as well as methods of evaluating forecasting models. We also cover basic univariate smoothing and decomposition forecasting methods, including moving averages, ARIMA, Holt-Winters, unobserved components models, and various filtering methods (Hodrick-Prescott filter, Kalman filter). Time permitting, we extend our models to multivariate modeling options such as vector autoregressive models (VAR). We also discuss forecasting with hierarchical data and the unique challenges that hierarchical reconciliation creates. The course uses the R programming language, though no prior experience with R is required.

This course provides an introduction to the operations research methods used in business. We briefly review the basics of calculus and linear algebra, then outline the conceptual foundations of economic modeling, and apply optimization techniques to various economic problems. The course provides a sound perspective on using operations research techniques in economic and managerial decision-making, which has become an increasingly sought-after skill. We work on various problems, including portfolio management, resource management, and environmental and energy-related regulations.

Machine learning is the design of algorithms that routinely learn and adapt with use to discover hidden properties, patterns, and trends in complex data. This semester-long course explores foundational methods, probability theory, and statistical methods, focusing on classifying data, recognizing patterns, formulating and testing hypotheses, and forecasting statistical trends that highlight potential tradeoffs and decision options by stakeholders. Topics include discrete and continuous random variables, the algebra of random variables, independence, central limit theorems, and Gaussian distributions (univariate and multivariate forms). Topics in statistics focus on regression theory and hypothesis testing.

This course introduces students to computer vision concepts and methods. Students learn how to conduct classification, detection, and recognition tasks. It covers the basics of computer vision, machine learning models for vision, convolutional neural networks (CNN) and transformer architecture, object detection and image segmentation, autoencoders and image manipulation, generative adversarial networks (GAN) for image creation, and multi-input models.

This course introduces students to natural language processing (NLP) concepts and methods. Students learn how to conduct both supervised and unsupervised NLP. The course covers the basics of NLP, text (document) classification, text summarization, text similarity and clustering, semantic analysis, sentiment analysis, and deep learning approaches (recurrent neural networks and transformer-based architecture).

This course provides an overview of the popular software packages currently used for data exploration, analysis, and visualization. The first part of the course emphasizes Excel and Tableau. The Excel portion covers basic charts and their use with pivot tables. The Tableau component introduces students to advanced data exploration and visualization methods through a variety of charts and dashboards. The second part of the course examines exploratory data analysis in R. Students learn how to write their own code for importing, cleaning, and exploring large datasets, as well as how to create, modify, and export complex charts and summaries for visual, qualitative, and quantitative analysis. The third part of the course provides an introduction to SQL databases, where students learn how to create SQL queries to select, filter, and manipulate data.

Working with data to produce results is the first step in effective modeling. Once obtained, results need to be transformed into insights and communicated—often to non-technical audiences. This course provides techniques for visualizing data, presenting insights, and communicating with a variety of audiences.