Course Descriptions for MS in Applied Data Science

Prerequisites: A Bachelor’s Degree and completion of an introductory statistics course

This course introduces students to the interdisciplinary field of data science. The emergence of massive datasets from diverse areas such as telecommunications, large-scale retailing, sports, healthcare, climate science, and social media provide the primary impetus for the field. This course will emphasize practical techniques that include cleaning and transforming data, exploring and analyzing data, summarizing and visualizing data, statistical inference, creation of statistical models, and communication of results. In addition, ethical implications of the choices made at different stages in a data science project will be explored. This course also introduces students to the scripting languages R and Python which will be used throughout the course.

Prerequisites: A Bachelor’s Degree and completion of an introductory statistics course

This course covers the fundamental Python programming concepts used in data science. Topics include variables, data types, control structures, functions, object-oriented programming, and programming libraries used for data manipulation and visualization. Students will learn how to read, write, and debug code following best software development practices.

Prerequisites: A Bachelor’s Degree and completion of an introductory statistics course

This course covers basic statistical skills for advanced work in data science and analytics. It begins with a review of descriptive statistics and contingency tables, before moving on to one-and two-sample methods of point estimation, interval estimation and hypothesis testing. The remainder of the course focuses on predictive modeling methods, including simple and multiple linear regression, logistic regression, and time series.

Prerequisites: (DSC 501 or DSC 502) and DSC 503

Communication is a critical yet often overlooked part of data science. It is not enough just to have technical know- how, data scientists need to be able to rationally justify their approach to a project, and then convince their audience (stakeholders) that their results should be utilized, and recommendations implemented. This course develops an understanding of theory and skills in constructing a relevant, ethical, and engaging message using data that tells a coherent, persuasive story to audiences of technical experts and non-experts.

Prerequisites: DSC 502

This course covers concepts related to the design and implementation of traditional databases and distributed systems for the management of big data. Topics include theory and applications related to efficient database models and queries, relational and non-relational databases, parallel and distributed processing, stream processing, and cloud-based computing.

Prerequisites: DSC 502 and DSC 503

This course covers standard supervised machine learning techniques including linear and logistic regression, support vector machines, and artificial neural networks; and unsupervised techniques for clustering and dimension reduction. Students will gain practical experience with using programming frameworks, software, and cloud platforms for developing and evaluating machine learning models for a variety of real-world applications.

Prerequisites: DSC 501, DSC 502, DSC 503 | Pre or Co-requisite: DSC 504

In a world of data superabundance, data visualization is one of the most powerful tools to explore, understand, and communicate patterns in data. This course will introduce students to data visualization design principles so that they can think critically about each design decision. Students will then apply these principles in the context of data analysis and visual storytelling using appropriate programming frameworks and software tools.

Prerequisites: DSC 501 and DSC 502

Note: This course may be taken with different topics up to 5 times for credit. Each special topic course will focus on an advanced topic in data science. The course will provide students with a broad background in the applications of data science, theory, and/or business applications. Special topics may include Business Analytics, Network Science, Web Programming, and Geographic Information Systems.

Prerequisites: DSC 506 and DSC 507

The Data Science Practicum is a project-based course where students work closely with outside sponsors and faculty for one or more semesters on an extensive data science project. Students will identify an application or problem in the area of data science or will be assigned a project by a sponsor or faculty member. The Practicum provides a cap-stone experience that requires the correct application of data science principles for the processing, analysis, visualization, and interpretation of data; and/or the development of novel methods for a unique data science task. The experience culminates in a written report and final presentation to the project sponsors and data science faculty. This course may be repeated up to two times for a maximum of 6 credits.