DSA-Data Science and Analytics

DSA G4413. Algorithm Analysis.3 Credit Hours.

(Crosslisted with C S 4413) Prerequisites: C S 2413 and C S 2813; or MATH 2513; or DSA 5005; and departmental permission. Design and analysis of algorithms and measurement of their complexity. This course introduces various algorithm design strategies--divide and conquer, greedy principle and dynamic programming--to solve a variety of problems using algorithms of various types: deterministic and randomized, serial and parallel, centralized and decentralized, and program based and circuit based. (F)

DSA G4513. Database Management Systems.3 Credit Hours.

(Crosslisted with C S 4513) Prerequisites: C S 2413 and C S 2813; or MATH 2513; or DSA 5005; and departmental permission. The design and implementation of a DBMS including data models, query languages, entity-relationship diagrams, functional dependencies, normalization, storage structures, access methods, query processing, security and transaction management, and applications. The impact of databases on individuals, organizations, and society, and legal and professional responsibilities including security and privacy will be discussed. A commercial DBMS is used. Students practice written communication skills. (F)

DSA 5001. Data Analytics and Media.1 Credit Hour.

Prerequisites: Departmental permission; graduate standing. This course covers the application of data analytics to the media environment. Students will learn the application and usage of data analytics in media and its effectiveness; and how data analytics provides research tools to collect audiences' opinion on political, social, public issues, and consumers' responses to the brand. (Irreg)

DSA 5005. Computing Structures.5 Credit Hours.

(Crosslisted with C S 5005) Prerequisite: CS 2334, MATH 1914 or MATH 1823 or with permission of graduate liaison. This course has three parts: discrete mathematics, object-oriented programming in C++, and data structures in C++. As part of the discrete mathematics students will be introduced to combinatorics, logic, relations, functions, computational complexity, automata, and graph theory. Students will be introduced to the fundamentals of object-oriented programming and learn to design, build, and analyze data structures using object-oriented principles and techniques. Credit hours earned for this course cannot be used to fulfill degree requirements for the B.S., M.S. or Ph.D. programs in computer science. (Irreg.)

DSA 5011. Introduction to R.1 Credit Hour.

Prerequisites: departmental permission; graduate standing. R is a free open source statistical programming language used by professionals in every field and industry. This introductory course aims to provide students with the fundamentals of R and R Studio. Instead of passively watching videos, students will apply R to solve real data problems while receiving instant and personalized feedback that guides them to the correct solution. (Irreg.)

DSA 5013. Fundamentals of Engineering Statistical Analysis.3 Credit Hours.

(Crosslisted with ISE 5013) Prerequisite: graduate standing. Introduction to probability, expectation, discrete and continuous distributions, sampling and descriptive statistics, parameter estimation, and statistical tests to aid decision making. The student will learn analysis techniques for verification of systems parameters. (F, Sp)

DSA 5021. Data Analytics Applied to Meteorology Data.1 Credit Hour.

Prerequisites: departmental permission; graduate standing. This course focuses on meteorology data that is stored regularly in space and time, so-called gridded data. For example, satellite or forecast data that is stored in a specific latitude-longitude grid, and available at uniform increments in time. Analysis of gridded data is abetted by programming in Python, offering an array syntax that exploits the uniformity of data. (Irreg.)

DSA 5031. Quasi-Experimental Methods in Econometrics.1 Credit Hour.

Prerequisite: graduate standing and departmental permission. A solid foundation in statistics and linear regression is helpful. Learn to use "quasi-experimental" methods to establish causal relationships in observational data. Learn the ideas behind the techniques of regression discontinuity, difference-in-difference, synthetic control, and propensity score matching; investigate how these methods can distinguish causality from correlation. Use real-world data sets to practice and master each technique. (Irreg.)

DSA 5103. Intelligent Data Analytics.3 Credit Hours.

(Crosslisted with ISE 5103) Prerequisite: graduate standing or permission of instructor; ISE 3293 or ISE 5013; CS 1313 or CS 1323. In our society, data is rapidly increasing in volume, velocity, and variety. At the same time computing power and the sophistication of data analysis techniques are increasing. However, even with the expanding capabilities, businesses and organizations often find themselves "data rich, but information poor." Intelligent Data Analysis is a holistic approach to addressing real-world data intensive problems that integrates human intuition with data analysis tools to best draw out meaningful insights. To this end, the course has four underlying themes: defining the Problem, understanding and coping with Data, selecting and using appropriate Analytical Tools, and discovering and communicating the Insight. Techniques covered include data cleansing and pre-processing, exploratory analysis and visualization, dimension reduction, linear and logistic regression, decision trees, and clustering. This course will introduce students to a powerful open source statistical programming language (R) and include extensive hands-on data analysis and team projects. (F)

DSA 5113. Advanced Analytics and Metaheuristics.3 Credit Hours.

(Crosslisted with ISE 5113) Prerequisite: ISE 5013, graduate standing or permission of Instructor. Explores advanced techniques for addressing complex optimization problems. Focus is on formulating mathematical models and developing problem solving strategies using methods in the context of Data Science and Analytics. Topics include continuous and combinatorial optimization with an emphasis on both traditional and modern heuristic techniques. (Sp)

DSA 5203. Time Series Analysis.3 Credit Hours.

Prerequisite: DSA/ISE/C S graduate standing or Departmental permission. This course will cover data mining and time series analysis. Modules include: statistical estimation, transformations and decomposition of time series, quantifying correlation structure in standard models, forecasting methods, linear least squares method, and volatility models. Students will utilize MATLAB Time Series Tool Box and open source programs in R. (Irreg.)

DSA 5303. Financial Engineering Analytics.3 Credit Hours.

Prerequisite: departmental permission or DSA/ISE/C S graduate standing. Course focuses on use of optimization and stochastic models to solve portfolio optimization problems; price derivative securities including energy and weather derivatives; and applications of financial engineering, including algorithmic trading, financial networks, pricing of real options, and the use of machine learning in pricing. Data driven models and big data mining in financial engineering will be also discussed. (Irreg.)

DSA 5403. Bayesian Statistics.3 Credit Hours.

Prerequisite: Departmental permission or DSA graduate standing. Course topics are models, probability, Bayes' Rule and R; inference to a binomial probability; and the generalized linear model. (Irreg.)

DSA 5900. Professional Practice.1-4 Credit Hours.

1 to 4 hours. Prerequisite: Completed or concurrent enrollment in DSA 5103, DSA 5113, DSA 4413, and DSA 4513. Graduate standing and departmental permission. May be repeated; maximum credit four hours. Participation in a professional experience with an approved project sponsor and topic. A written report detailing the responsibilities and results of the experience is required upon completion along with an oral presentation. (F, Sp, Su)

DSA 5970. Special Topics/Seminar.1-3 Credit Hours.

1 to 3 hours. Prerequisite: permission of instructor. May be repeated with a change of subject matter; maximum credit 12 hours. Selected topics of current research interest not covered by regularly scheduled coursework. (F, Sp, Su) (Irreg.)