Summer short courses are designed to enhance the elective offerings available to IAD students, and for students in related programs at UB.
These ‘bite-size’ courses are designed to:
Students can ‘stack’ these 1-2 credit offerings to fulfill IAD degree requirements or enhance knowledge in critical areas that will make them more competitive in the marketplace. These electives are approved for students in both data science programs in IAD, to satisfy either the elective requirement or to replace the project course to finish the graduation requirements.
Non-IAD masters students interested in taking these courses for elective credit towards their degree should seek approval from their department before requesting registration.
These summer courses run on non-standard class dates. The financial liability and add/drop dates vary for each individual course and students are responsible for reviewing these dates prior to enrollment via the student accounts website.
This hands-on course teaches students how to build batch and real-time data and machine learning systems using AWS technologies, progressing from data engineering to data science to MLOps. Students start by designing ingestion and transformation pipelines and performing scalable ETL and analytics with services such as AWS Glue, Amazon Athena, and PySpark, then move into feature development, experimentation, and model training with Amazon SageMaker. Finally, they operationalize and deploy solutions by building end-to-end batch inference workflows and a real-time streaming application, emphasizing monitoring, reliability, and production-ready practices on AWS. Note: Students are responsible for all AWS/cloud-related expenses.
This short, project-based course introduces the core ideas behind modern recommender systems through the design and implementation of a single end-to-end recommendation pipeline in Python. Students will build a working recommender using collaborative filtering and latent factor models and learn how to evaluate and improve it under real-world constraints such as data sparsity and cold-start users. Rather than surveying many algorithms, the course emphasizes depth, implementation, and system thinking. By the end of the course, students will have a functioning recommender system and an understanding of the key design trade-offs behind real personalization engine
Description: This course provides a hands-on introduction to time series forecasting using both R and Python. Students will learn core concepts such as trend, seasonality, stationarity, and autocorrelation, and apply modern forecasting techniques including ARIMA, exponential smoothing, and machine learning–based models. Students will develop the skills necessary to work with time series data, build and evaluate forecasting models, and communicate results effectively. No prior experience with time series analysis is required; basic familiarity with R or Python is helpful but not essential.
This course introduces the fundamentals of network analysis, inference, and visualization. Students will learn how to construct networks from data, interpret key structural properties (e.g., centrality and clustering), and apply basic network inference methods, including an introduction to Bayesian networks. Emphasis is placed on clear, effective visualization and communication of network-based insights.
IAD Master's students should fill out the summer formstack registration in order to enroll in the CDA courses.
Non-IAD masters students should confirm with their department if these classes can be used for their degree requirements.
Email cda-grad@buffalo.edu for questions or assistance with class registration.