ACADEMICS

This course examines how statistical methods lead to understanding and describing data. We use R/RStudio to review basic data exploration and statistical methods. Topics covered include simple descriptive statistics through hypothesis testing and modeling.

In this course, students gain competence in practical database, data warehousing, and data management skills with emphasis on query, data modeling, ETL, and data management. They will also become familiar with major elements of the big data ecosystem.

We will study the fundamental principles and techniques of data mining in order to extract useful information and knowledge from data. We will improve our ability to approach problems "data-analytically,” examine real-world examples that place data mining in context, and apply data-mining techniques while working hands-on with data mining projects. The course will provide an understanding of the general framework for building and evaluating predictive models, both for classification and numeric prediction data mining tasks. The course will cover supervised predictive modeling techniques as well as unsupervised predictive modeling techniques.

Learn modern network analysis methods and how to apply them to network data. Study the latest in theory, methods, and substantive applications. This course covers the application of network theory to the study of careers, competition, innovation, inequality/stratification, IT-mediated networks, network formation, and network dynamics.

This is an introduction to basic concepts in machine learning, both supervised and unsupervised. The basic ideas of neural networks will be presented. Machine learning from data streams (online learning) using stochastic gradient descent is also covered.

Where the art of graphic design meets with the science of data analytics. Learn how to perform exploratory analysis through visualization, how to create professional-looking visualizations for use in business reports and presentations, and how to design interactive visualizations and dashboards.

Delve into a number of selected current and emerging data analytics areas that are increasingly important for organizations. Areas include advanced elements of the predictive modeling process, ensemble methods, cost-aware data analytics, mining text and data, recommender systems, and other advanced topics.

This course introduces students to optimization and simulation, powerful techniques for better decision-making (in particular, linear, integer and non-linear programming), and Monte Carlo and discrete event simulation, and discuss their application to problems in business and data analytics.

Deep learning models aim to recognize complex patterns in pictures, text, sounds, and other data to produce accurate insights and predictions, and reinforcement learning methods focus on learning how to map situations to actions, so as to maximize a reward. ISOM 678 introduces some of the key ideas and techniques developed from the machine learning communities on deep learning and reinforcement learning, with an emphasize on the practical understanding and implementations of these techniques in real world business problems. In this course, algorithms and concepts are presented to build intuition for how different methods work, without advanced mathematics. Topics include single- and multi- layer networks, convolutional and recurrent neural networks, multi-armed bandits, finite Markov decision processes and on-policy and off-policy data methods. Programming is central to the course and is based on the R and Python programming languages.

The course introduces modern data-driven supply chain management techniques. Specific focus will be on supply chain resiliency and efficiency. The topics include deep-tier supply network visibility, supply risk identification, demand and lost sales estimation, data-driven sales and operations planning, and inventory management. We will use graph-theoretic, simulation, econometric, and operations research methods relevant to supply chain management.

The MSBA Analytics Practicum leverages skills and techniques learned throughout the course of the program and applies them to real-world business situations. Students formally define problems, clean data, aggregate with other data sources, and identify and use appropriate analytical techniques to address questions.

This course uses analytic methods to solve marketing problems (including pricing, customer relationship management and sales forecasting). We emphasize the development of tools that can be implemented in practice to support decision making and rely on frequentist and Bayesian methodologies.

This course focuses on tools and techniques applicable to decision making in sports. The analytical foundations for the class are classical statistical and optimization techniques. We solve sports problems using tools such as linear regression, logistic regression, Markov chains, and optimization.

This course introduces students to statistical and computational methods used in employee recruitment, selection, promotion and turnover. A significant portion of the course is devoted to experimental methods designed to test the efficacy of HR policies before an organization implements them.