Advanced Analytics Concentration
M.S. in Data Science and Business Analytics: Advanced Analytics Concentration
This concentration is made up of three core courses and three concentration courses, then culminates in an interdisciplinary practicum that will connect students to the real-world. All the core and concentration courses will be three (3) credits each and will be offered by the College of Engineering and the Mike Ilitch School of Business. The program will culminate with a six (6) credit Interdisciplinary practicum which will pull together a variety of subject material covered in the core courses and give it a real-world application. Elective courses (6 credits) can come from other concentrations (assuming the student has the right pre-requisite knowledge) or from outside the program.
MODULE 1: CORE COURSES (9 CREDITS)
Course DSB-6000: Data Science Strategy & Leadership (3 Credits) - Provides an understanding of how organizations can leverage data science and analytics to gain competitive advantage and how to use the data to align with a company's mission and goals. Students will learn how organizations derive business value/impact, and return on investment, and the importance of interpreting and communicating the business case.
- Understand how organizations can use data to align with their mission and goals
- Understand the role of data science in organizational strategy and how organizations can leverage information to gain competitive advantage.
- Understand the challenges of data driven businesses –how can organizations start to use their data to deliver actionable business insight.
- Gain an introductory knowledge of data science tools and new technologies tools that are useful in extracting intelligence and value from data needed to solve next generation data challenges
- Identify the application of data science tools to reveal business opportunities and threats.
- Identify the challenges posed by the ability to scale and the constraints of today's computing platforms and algorithms
Course DSA-6000: Data Science & Analytics (3 Credits) - Basic data science and analytics concepts covered through case studies, success stories, and a semester project that cuts across all course modules.
- Discuss the elements of a data science and analytics project life-cycle, starting with business need to solution deployment and sustainment.
- Apply core data science and analytics techniques, tools and technologies
- Apply statistical and machine learning tools and techniques to tackle various aspects of big data analytics projects
- Make analytics actionable for business effectiveness and effectively engage business users and communicate findings.
Course DSE-6000: Computing Platforms for Data Science (3 Credits) - Covers an overview of various computing platforms for developing, deploying, configuring a wide range of data science applications for different domains. The programming models, characteristics of supported workload, and management of performance, cost and scalability will be compared side by side.
- Develop the skills necessary for creating and deploying efficient data science and analytics applications.
- Analyze major distributed and parallel computing frameworks, such as MapReduce, Spark, and traditional high performance computing (HPC) systems
- Compare programming models for batch, interactive, and streaming applications
- Use and manage performance, cost, and scalability of hosted data platforms and the cloud based solutions
- Apply criteria for choosing and configuring data science computing systems for specific applications.
MODULE 2: ADVANCED ANALYTICS CONCENTRATION COURSES (9 CREDITS)
Choose three courses from the list below.
Course DSA-6100: Statistical Methods for Data Science & Analytics (3 Credits) - Statistical methods and techniques required for data science and analytics applications covered through case studies, success stories, and a semester project that cuts across all course modules.
- Apply the concepts and procedures of inferential statistics including probability, confidence intervals, and hypothesis testing for data science analysis
- Use statistical software to conduct a variety of statistical analyses, including testing of statistical assumptions, data transformations, and validation of statistical findings
- Apply the statistical learning and data analysis strategy to solve real-world problems and test hypothesis, with specifications for data elements, requirements of the statistic, and limitations to the interpretation
- Discuss results of statistical analyses efficiently, and prepare written reports and technical illustrations that summarize background, analysis procedures, and interpretation of technical results
Course DSA-6200: Operations Research (3 Credits) - Mathematical optimization models that come into play in data science and analytics applications covered through case studies and a semester project. Heuristic solution approaches will also be addressed along with sensitivity analysis techniques.
- Develop and apply skills in recognizing & formulating deterministic and stochastic optimization models including: constraints, objective functions and decision variables.
- Develop an appreciation for the role of sensitivity analysis in analyzing a system
- Apply the appropriate types of mathematical models and methods in their respective data science and analytics applications.
- Develop and apply key meta-heuristics solutions for challenging data science and analytics applications.
- Analyze, formulate, solve and discuss a data science and analytics business case problem and effectively justify your model and solution in a written and oral report.
Course DSA-6300: Decision Analysis & Simulation (3 Credits) - Coherent approach to decision making, developing rules of thought to transform complex decisions into simpler decision situations covered through case studies, success stories, and a semester project that cuts across all course modules. Discusses role of discrete-event simulation for improving decision support.
- Identify common biases and barriers to quality and efficient decision making
- Recognize opportunities to apply decision analytic tools
- Frame and structure complex decision problems
- Analyze decisions involving uncertainty
- Build discrete event simulation models to inform planning and decision making
Course CSC-7810: Data Mining: Algorithms and Applications (3 Credits) - Application of various basic/advanced data mining techniques to real-world problems. Prerequisite: CSC 5800 with a minimum grade of C.
Course CSC-7825: Machine Learning (3 Credits) - Supervised learning including regression, kernel-based, tree-based, probability model based and ensemble learning; unsupervised learning including distance based and model based; Markov Chain Monte Carlo (MCMC) methods; graphical models; current topics from literature. Prerequisite: CSC 5825 with a minimum grade of C.
Course ISE-7860: Intelligent Analytics / Deep Learning (3 Credits) - Computational intelligence and machine learning methods (primarily neural networks and deep learning) used to solve complex analytics problems and develop decision support systems. Project-centric approach with the goal of developing several analytics solutions for real-world problems.
MODULE 3: ELECTIVES (6 CREDITS NEEDED)
Elective courses can come from other concentrations within the Data Science & Business Analytics program or from outside the program. See Elective Courses page for approved course list.
MODULE 4: APPLIED ANALYTICS PRACTICUM (6 CREDITS)
Course DSA-7500: Practicum (6 Credits) - Application of theoretical knowledge acquired during the Data Science and Business Analytics program to a project involving actual business problems/opportunities and data in a realistic setting. Engages the entire process of solving a real-world data science and business analytics project including: setting the project scope, collecting and processing data, applying analytic methods and presenting the developed solution platform. Both the problem statements for the project assignments and the datasets originate from real-world domains.
- Manage business opportunities from problem/opportunity recognition through delivery and deployment of effective solutions
- Scope the project, collect and process real-world data, design best methods to solve the problem, implement a solution, and quantify the robustness and accuracy of proposed models
- Present proposals on how to approach the problem and findings from solutions
- Work in project teams to develop successful solutions
- Write project reports for evaluation and gaining support