Industrial and Systems Engineering Master of Science Program
Data Analytics and Data-Driven Optimization
Our society is undergoing a major transformation with the use of large-scale, diverse, and high-resolution
data sets that allow for data-intensive decision-making and optimization. There is an imperative need for
data analytics—means and methods for using large data sets and computer models to drive business
value, understand human relationships, and improve decision-making. The powerful combination of big
data analytics with optimization has been successfully demonstrated and will be increasingly needed in the
management of:
- healthcare and transportation networks
- retail and financial decision making
- supply chain and logistics systems
- large scale information systems
- manufacturing operations
- energy and smart grids
- social networks
The ISE Masters Program in Data Analytics and Data-Driven Optimization is designed to provide students
with a strong background in analytics, data science, computer science and optimization methods. The
track requires a sequence of courses in:
- computer science
- operations research
- cognitive engineering
- probability and statistics
Additional electives are also recommended in Business, Computer Science Engineering (CSE) and
Industrial and Systems Engineering (ISE) and Statistics (STAT).
Students will be prepared in the use of critical tool sets necessary for managing, visualizing, and extracting
useful information from big data, as well as powerful skill sets such for modeling, simulation, optimization
and decision analysis in order to support efficient data-driven decision making.
Admission Requirements.
Prior to admission, students interested in admission to this Masters Program
should be proficient in the following areas1:
- Vector calculus
- Computer programming (e.g., C, C++, Java)
- Calculus-based probability
- Probability-based statistics
- Linear algebra
Graduation Requirements.
All Analytics Graduate Students must satisfy degree requirements defined in the Industrial and Systems Engineering Graduate Student Handbook
To complete the ISE Masters Program in Data Analytics and Data-Driven Optimization, students must complete a total of 36 graduate credit hours. The course work consists of:
- 12 semester hours of ISE courses, 10 semester hours of CSE courses, 4 semester hours of STAT courses, and 3 semester hours of Visual Analytics (in total 29 credit hours)
- 2 semester hours of ISE 7883 (Department Seminar) and one 5000-level or higher ISE course in manufacturing or human factors, subject to approval of the advisory committee, in order to meet the ISE secondary sub-discipline requirement. (in total 5 semester hours )
- A project, exam or Masters thesis designed to meet the exit requirements of the Data Analytics and Optimization MS Program:
- M.S. students can meet the exit requirement by 1) doing a Masters thesis (4 units); or 2) earning a B or higher in a 5000- or higher- level Analytics elective course that is at least 2 units and has a project requirement; or 3) passing the M.S. Exit Examination.
- M.S. students who are not doing the thesis option and did not receive a B or higher in a 5000-level Analytics elective course with a project requirement may instead take the M.S. Exit Examination.
- The M.S. Exit Examination is administered annually during the week after Spring final examinations have been completed. Any ISE graduate student who achieves an overall GPA (including all graduate courses taken at OSU) of 3.00 is eligible to take the exam.
M.S. Exit Examination for ISE M.S. Analytics students
- M.S. students who are not doing the thesis option and did not receive a B or higher in a 5000-level Analytics elective course with a project requirement may instead take the M.S. Exit Examination.
- The M.S. Exit Examination is administered annually during the week after Spring final complete. Any ISE graduate student who achieves an overall GPA (including all courses taken at OSU) of 3.00 is eligible to take the exam. Those students who are planning to graduate in Fall should take the exam in the preceding Spring semester. The process to sign-up for the exam will be announced during Spring semester. Students intending to take the exam must sign-up before the announced deadline, so there is sufficient time to check that the grade eligibility requirement is satisfied.
- The intent of the exam is to verify that students are sufficiently well grounded in the “fundamentals of OR.” For example, the exam might cover the following topics:
- Optimization: Integer and Linear Programming Formulations and Solution Methods; Linear Programming Theory and Duality; Complexity Theory; Convexity
- Stochastic Processes: Random Variables; Probability Distributions; Conditional Probability and Expectations; Random Number Generation; Simulation Theory
- Statistics: Parametric and Non-Parametric Hypothesis Testing; Distribution Fitting; Regression
- After the exams have been completed, the OR Faculty meet to discuss each student’s performance on the exam and performance in classes taken. Based on this, the faculty determine whether each student has “passed” or “failed” the examination.
- A student who has failed the examination, may be deemed eligible to retake it. Students who are deemed eligible to retake the exam must do so the next time that it is offered. No student will be eligible to take the exam more than twice.
The following course requirements focusing on data analytics and optimization:
Required Data Analytics and Optimization Courses
(students who have previously completed the equivalent of these courses can select substitutes from the list of recommended electives)
- ISE (12 credit hours)
- ISE 5110 Design of Engineering Experiments (3)
- ISE 5200 Linear Optimization (3)
- ISE 6300 Simulation for System Analytics and Decision-Making (3)
- ISE 7250 Operations Research Models and Methods (3)
- CSE (10 credit hours)
- CSE 5023 Software II (Java II) (3)
- CSE 5241 Introduction to Database Systems (2)
- CSE 5032 Foundations I: Discrete Structures (2)
- CSE 5243 Introduction to Data Mining (3)
- STAT (4 credit hours)
- Stat 6450 Applied Regression Analysis (4)
- Visual Analytics (3 credit hours)
- One of the following –
ISE 5760 Visual Analytics and Sense Making2 (3)
CSE 5544 Introduction to Scientific Visualization (3)
Additional ISE Requirements
- Seminar (2 credit hours)
o ISE 7883: Seminar (2)
- One 5000-level or higher ISE course in manufacturing, or human factors:
Recommended courses-
o ISE 5682 Fundamentals of Product Design Engineering, or
o ISE 5600 Principles of Occupational Biomechanics and Industrial Ergonomics, or
o ISE 5700 Cognitive Systems Engineering
Possible project courses and recommended electives
- ISE
o ISE 6220 Network Optimization
o ISE 6290 Stochastic Optimization
o ISE 7100 Advanced Simulation
o ISE 7210 Large-Scale Optimization
o ISE 7230 Integer Optimization
o ISE 7420 Sequencing and Scheduling
- CSE
o CSE 5523 Machine Learning and Statistical Pattern Recognition (3)
o CSE 5331 Foundations II: Data Structures and Algorithms (2)
o CSE 5122 Data Structures Using C++ (3)
- STAT
o PUBHBIO 7220 - Applied Logistic Regression
o Stat 5740 Introduction to SAS Software (2)
o Stat 6550 The Statistical Analysis of Time Series (2)
o Stat 6740 Data Management and Graphics for Statistical Analyses (3)
