Artificial Intelligence & Learning Analytics

Concentration 1: AI & Learning Analytics

Learn how to use data and AI to better understand, and improve, how people learn. 

The AI & Learning Analytics concentration prepares students to apply data science, artificial intelligence, and learning science to real-world educational challenges. Combining research, technical skill-building, and hands-on application, the program equips you to turn complex data into meaningful insights that inform teaching, learning, and decision-making.
​
Courses are taught by leading faculty and designed to be accessible to learners from a wide range of academic and professional backgrounds.

Who This is For

This concentration is designed for professionals across education and related fields who are interested in using data and AI to improve learning outcomes. 

You may be a good fit if you: 

• Want to use data to improve learning across classrooms, programs or systems. 

• Want to build practical skills in analytics, AI, and data interpretation 

• Have little or no prior experience in coding or AI, but are ready to learn 

• Are looking to move into or grow within roles that involve data-informed decision making 

You’ll begin with the fundamentals and build toward more advanced applications over the course of the program.

Vertical Divider

What You'll Learn

You’ll develop both the technical skills and conceptual foundation needed to work confidently with educational data. This includes: 

• Core principles from learning and cognitive sciences that shape how we interpret data about learning 

• How to access, clean, manage, and analyze data from digital learning environments 

• How to communicate insights clearly through writing and data visualization 

• How to apply AI tools and methods in educational contexts 

• An understanding of ethical considerations and responsible data use ​

Vertical Divider

What You'll Do

Throughout the program, you will:  

• Work with real or simulated datasets from learning environments 

• Apply analytical tools and methods to explore questions about learning 

• Complete case studies and project-based assignments 

• Collaborate with peers in a cohort-based environment 

• Engage closely with faculty and subject-matter experts 

• Complete a capstone project focused on a real-world problem or area of interest ​

Career Outcomes

Program Highlights

Duration: 12 months
Format: part-time, online
Structure:

• Summer 1: one course
• Fall-Spring: two courses per quarter
• Summer 2: two courses

Culminating experience

• Master’s capstone project
• Graduation event

Learning Model: cohort-based Cost

• Join our interest list to learn more about cost and available scholarships

Vertical Divider

Graduates are prepared for roles that sit at the intersection of education, data, and technology. 

Potential paths include: 

• Educational data analyst 

• Learning analytics specialist 

• EdTech product or research roles 

• Program evaluation and research positions 

• Data-informed roles within schools, districts, or organizations ​

Curriculum

Introduction to educational data science

This course will teach you how to use R (for beginners) or advanced techniques (for experienced users) to wrangle, analyze, and visualize education data. In addition, you will learn how to think with and about data in ethical ways. You will explore questions with data and communicate results using R-Markdown, which lets you build interactive lab notebooks and rich data visualizations. In addition to working with traditional data sources (e.g., gradebook data, institutional data), students will also learn how to clean, explore, analyze, and visualize clickstream data obtained from learning management systems. By the end of this course, you will be able to transform data into insights that instructors can use to better understand their students and improve learning outcomes.

Introduction to AI in Education

This course introduces how artificial intelligence—especially generative AI—is being used to support teaching, learning, and educational research. You’ll learn key concepts and practical strategies for using AI thoughtfully, effectively, and responsibly in real educational settings. Throughout the term, you’ll build a digital portfolio featuring concrete examples, an annotated bibliography of research and resources, and a final project aligned with your professional interests. By the end, you’ll be able to evaluate AI tools critically and design meaningful, accessible learning experiences that make smart use of them.

Foundations of Learning Analytics

This course will provide students with a general survey of learning analytics, emphasizing its application across various educational contexts, rather than its underlying algorithmic details. In particular, we will discuss the foundations of learning analytics in the context of relevant sociotechnical shifts and theoretical frameworks; discuss emerging forms of assessment and common data analytic approaches, including those using artificial intelligence; review learning analytical tools and illustrative studies, and design analytics for each student’s research area. Overall, this course provides a comprehensive, theory-driven overview of learning analytics to orient students to this nascent field and prepare them for advanced research/practice in learning analytics.

Educational Statistics and Data Analysis

This course will introduce students to key statistical concepts and techniques for exploring and analyzing educational data using R. These concepts include understanding estimation and uncertainty in data, sampling, sampling error, hypothesis testing, descriptive statistics, statistical tests of association (e.g., correlation, independent tests), and linear models (e.g., regression).

​Students will design a research hypothesis for testing, implement appropriate statistical procedures, and write a formal research report. Unique to this course is that we will explore these concepts using a real data set from an online undergraduate course. This data set contains demographic, gradebook, survey, and clickstream data.

Data Visualization and Communication

Students in this course will learn about the theories and techniques of data visualization, with a focus on applications in education and learning analytics. The course will provide an introduction to topics such as perception and cognition, data representations, and visualization techniques for specific data types. Students will also gain experience in utilizing human-centered design approaches and implementing different workflows: from creating visualizations with standard packages (e.g., R/Shiny) to designing new visualizations with prototyping tools (Figma). Finally, the course will focus on the unique needs and design challenges for visually and verbally communicating data to improve teaching, learning, and equity in education settings.

Applications of AI in Education

This course will allow students to explore various applications of AI in education, by learning about the theories and methods underpinning these applications and building their own AI tools. The course will specifically look at applications that contribute to three foundational aspects of education: assessment, learning, and instruction. Students will (a) be exposed to some of the key theories and controversies around these topics in education; (b) learn about state-of-the-art algorithmic approaches to assessment, learning, and instruction; and (c) gain hands-on experience with these algorithms through programming and data-mining exercises. Specific topics include item response theory, computerized-adaptive testing, learning curve analysis, knowledge tracing, intelligent tutoring systems, constructionist microworlds, and generative AI.

Educational Research and Evaluation

This course will cover the theory and methods of educational evaluation and research, with a focus on digital learning environments, and how they can be used in conjunction with learning analytics to illuminate students’ learning processes and outcomes. Topics addressed include measurement and sampling; validity, reliability, and assessment; correlational and survey research; experimental and quasi-experimental studies; observation and interviews; design-based research;  qualitative and quantitative data analysis; approaches to educational evaluation; and the role of artificial intelligence in facilitating educational data collection and analysis.

Special Topics in AI & Learning Analytics

We use measurement and assessment as a way to answer questions through use of psychological and educational tests and surveys. These tests cover many different domains (e.g., intelligence, cognition, personality) and take many different forms. These however all rely on psychometrics, which is a field of study dedicated to the theory and technique underlying the measurement of psychological phenomena (e.g., knowledge, abilities, attitudes, and personality traits).

In this course, we focus on appraisal and development of measures. We will consider measurement theory and its application in education using a classical test theory approach. Students will have the opportunity to apply aspects of psychometric theory including scaling, test construction, reliability and validity assessment, and item analysis to their own projects. Cross-cultural, cross-linguistic, and bilingual issues in test performance, item selection, and development will be considered.

Capstone in AI & Learning Analytics

Students in this final course will work closely with the instructor to devise an independent learning analytics project, implement this project, and present final analysis and results in the culminating program expo. Students will travel to UCI for a final two days as a cohort, where they will present their final capstone projects, interact with incoming cohorts to the program, and meet industry professionals in networking events.