Predictive Modeling and Student Learning Analytics
Start Any Time
Work on your pace and you will have instructors available to help you answer any questions.
Duration
Approximately 4 weeks, 3-4 hours/week
Fee*
$1500 Professional Rate
$500 Full-time Student Rate**
*Have you taken one of our courses before? Refer a friend or colleague and get 20% off any future course – they’ll get 20% off a course of their choosing, too! Just have the person you refer email us at learnlab-help@lists.andrew.cmu.edu with your name and email address.
**Proof of full time student enrollment required. Acceptable forms of ID include a letter from your university’s registrar office or an unofficial transcript. Email your documents to learnlab-help@lists.andrew.cmu.edu.
Certificate Course Description:
This course provides an in-depth introduction to predictive modeling techniques used in the analysis of student learning data. You will learn how to apply data-driven approaches to forecast student outcomes, uncover learning patterns, and support timely educational interventions. The course begins with foundational concepts in regression analysis and guides you through the process of selecting and engineering features from educational datasets.
Building on this foundation, you will explore student modeling and knowledge component (KC) modeling to represent learners’ evolving knowledge states. You will then apply knowledge tracing methods to estimate student learning over time, gaining insight into both mastery and learning trajectories. Emphasis is placed on model evaluation and refinement to ensure predictive accuracy and educational relevance. Through a series of hands-on projects, you will gain practical experience using real-world data and develop the skills necessary to construct, interpret, and improve predictive models in educational contexts.
Module 1: Item Response Theory
- Explain the Fundamentals of Item Response Theory and Its Distinctiveness
- Define and interpret the main parameters in Item Response Theory: Θ (latent trait estimate), a (item discrimination/sensitivity), b (item difficulty/location), and c (guessing)
- Apply IRT in Educational Data Mining (EDM) and Analytics
- Evaluate and Design Assessments Using Item Response Theory
Module 2: Feature Engineering
- Explain the concept and purpose of feature engineering, and apply it to enhance a model’s predictive power
- Select the right feature distillation technique for a given context
- Evaluate the effectiveness of newly engineered features on model performance
- Apply strategies to avoid the risks of overfitting through excessive feature engineering
- Apply feature engineering specific to educational data
Module 3: Student Models and KC Modeling
- Evaluate the quality of a KC model
- Improve upon existing KC models
Module 4: Knowledge Tracing
- Define the core concepts: Model Tracing, Knowledge Tracing, and Cognitive Mastery
- Analyze the two-state learning model and performance assumptions including ‘slip’ and ‘guess’ in Knowledge Tracing
- Explain how Knowledge Tracing is used to predict student performance
Module 5: Course Project or Final Exam
You’ll have an opportunity to do a little project where you will solve Colab notebook exercises, one corresponding to every module. That will provide you with a nice experience to apply the fundamentals you will learn in the modules to a larger, more authentic, context. It will be self-graded and you will receive a sample solution.
You will have an alternative option to take a final exam where you will answer 20 questions. The exam can be taken multiple times and each time new questions are randomly selected from a pool of questions.
You are also free to do both the course project and the final exam, we will consider the one in which you score more for counting towards the certificate.
Basic knowledge of Exploratory Data Analysis and Classifiers in Educational Data Science is desired.
No programming prerequisites but experience with a programming language (e.g Python) will be helpful.
Educators, data scientists, and learning engineers seeking to gain hands-on experience in predictive analytics, enabling them to develop data-driven insights for personalized learning, intervention design, and student success prediction.
What you'll learn
This course will help you:
- Apply Item Response Theory (IRT) to model student ability and design valid, insightful assessments
- Use feature engineering techniques to enhance model accuracy and interpretability in educational datasets
- Develop and evaluate student models and knowledge component (KC) models to represent and improve understanding of learning processes
- Implement knowledge tracing methods to predict student mastery trajectories and support timely educational interventions
Course Instructors
Dr. Paulo Carvalho
is an assistant professor in the Human-Computer Interaction Institute. His research explores how AI can revolutionize learning through the creation of engaging, practice-first and practice-only environments. Using data analytics and computational modeling, he investigates patterns in student learning, motivation, and interest to develop precise models that enhance educational experiences. His current work examines how generative AI can transform practice-focused approaches, simultaneously boosting student engagement while enabling teachers to provide more personalized support…..
Dr. John Stamper
is an Associate Professor of Human-Computer Interaction at Carnegie Mellon University. Dr. Stamper has a PhD in Computer Science from the University of North Carolina at Charlotte. His main area of research is focused on using “Big Data” from educational systems to improve learning. He is also the lead researcher behind DataShop, which is the largest open repository of log data from learning systems….
Certificate
Upon successful completion of the program, participants will receive a verified digital certificate of completion from Carnegie Mellon University’s Open Learning Initiative.
In addition to the knowledge and immediately applicable frameworks you will gain by attending your selected courses, you will benefit from:
- A digital, verified version of your Executive Certificate (Smart Certificate) you can add to your resume and LinkedIn
- Networking with a global group of your peers and instructors for advancing your career
Register Now
Register and start taking the course in three steps:
1. Enter your name and email address.
2. Create your account here to access our learning platform.