Completing this degree will help you understand how to gather and analyze data; how to identify trends and patterns in the data to better predict future events; how to use data to make decisions in complex, dynamic environments; and how to hedge against risk and account for uncertainty. Courses are taken in the College of Engineering’s Industrial Engineering & Operations Research department. Berkeley Faculty teaching these courses include Professor Adler and Professor Schruben.
- Optimization Analytics core MEng course – 3 units
- Risk Modeling, Simulation & Data Analytics core MEng course – 3 units
- Descriptive Analytics course – 3 units
- Predictive Analytics course – 3 units
IEOR 240 Optimization Analytics
This is an exclusive Masters of Engineering course. Computing technology has advanced to the point that commonly available tools can be used to solve practical decision problems and optimize real-world systems quickly and efficiently. Course topics will include techniques such as linear, integer, non-linear and multistage programming, and metaheuristics, applied to problems in planning, logistics, finance, energy and other domains.This course will focus on:
Computing technology has advanced to the point that commonly available tools can be used to solve practical decision problems and optimize real-world systems quickly and efficiently. This course will focus on
- Understanding and using these tools to model and solve complex real-world business and engineering problems
- Analyzing the impact of changing data and relaxing assumptions on these decisions, and
- Understand the risks associated with particular decisions and outcomes
- Introducing the mathematical concepts behind these tools
IEOR 241 Risk Modeling, Simulation, and Data Analysis
This is an exclusive Masters of Engineering course, in which students will develop a fundamental understanding of how randomness and uncertainty are the root causes of risk in modern enterprises. The technical material will be presented in the context of engineering team system design and operations decisions case studies.
Students will learn techniques for measuring and controlling risk that are critical in designing and managing robust, large-scale, complex global systems. Student teams will use this technology to:
- Learn the strengths and weaknesses of different approaches, giving them a foundation for selecting methodologies and software that are appropriate for different classes of problems.
- Learn how to model random processes and experiment with simulated systems.
- Be introduced to the different technologies used to develop make decisions where there is uncertainty.
- Understand various human decision-making approaches: intuition, analysis, consensus, guessing, etc.
- Become critical consumers of the management sciences – learn to question authority.
- Learn to communicate their ideas and solutions effectively in written reports.
- The course is a mixture of modeling art, analytical science, and computational technology.
IEOR 290: Fundamentals of Machine Learning & Data Analytics
This course introduces and motivates the fundamental concepts and theory underlying algorithms for machine learning and data analytics. Specifically, the course focuses on regression and classification algorithms, neural net networks, and graphical models, as well as data analytics. The methods studied include Bayesian inference from large-scale unstructured data and generative models to create data sets having specific properties for testing the robustness of optimization and simulation models. Upon successfully completing the course, students will be prepared with a basic background enabling them to further study, develop, and apply machine learning algorithms in data analytics.
- Background in probability, graph theory, decision theory and information theory
- Probability models for estimation and inference
- Graphical models and inference
- Classification Mixture Models and Expectation-Maximization (EM) algorithm
- Sampling Methods
- Neural Nets
IEOR 242: Applications in Data Analysis
This course is one of two technical electives, along with IEOR 290, a masters-level course on predictive analytics and theory, that together create the evening Master of Engineering in Industrial Engineering & Operations Research concentration in Decision Analytics.
This course applies foundational concepts in programming, databases, machine learning, and statistical modeling to answer questions from business and social science. The goal is for students to develop the experience and intuition to gather and build new datasets and answer substantive questions. On any given week, the theoretical basis for an analysis technique will be reviewed, the higher-level objective and research question debated, and potential approaches discussed. A number of real and very large datasets will be available for the final project; students will be expected to apply the appropriate method to a given dataset and by the end of the semester, demonstrate the judgment to pick the best techniques for a new dataset and given research question.
IEOR 290-04: Modern Optimization for Statistical Learning
This course will examine special topics at the interface of optimization, statistical learning, and data-driven decision-making. A central focus will be on computational guarantees and theoretical analysis of algorithms for large-scale convex optimization problems. The course will study algorithms that apply to a broad range of problems, interweaved with applications to exemplary problems from machine learning and examples of how to exploit problem structure to enhance algorithmic performance. Please Note: This is an advanced technical elective course.
IEOR 290-05: Technology Strategy in Emergent Industries
This course will use a combination of case studies, lectures, guest speakers, labs, and original research to study the strategy dynamics in industries that are emerging from new and breakthrough technologies. We will focus on the Augmented and Virtual Reality (AR/VR) industries as a specific example. Case studies will be discussed from similar industries and a general technology strategy framework will be developed. Students will form teams and study one firm in the industry in depth; teams may be paired with their closest competitor and be asked to debate which firm will do better as the industry matures.