Unsupervised learning for social systems

Sat, 30 May 2026 00:00:00 +0000

Many social datasets arrive without clean labels. We often do not know in advance what kinds of students, firms, neighborhoods, conversations, or cultural trajectories should exist in the data.

Unsupervised learning helps make that uncertainty productive. Clustering, embeddings, dimensionality reduction, topic models, and anomaly detection can expose structure that is hard to see with standard summaries. The key is not to treat these methods as automatic discovery engines, but as disciplined ways to generate hypotheses and compare representations.

For CRiSS-LAB, this matters because many of our questions are relational and behavioral: how students organize into groups, how scientific attention decays, how cities constrain movement, and how cultural systems remember. Good unsupervised workflows give us a way to explore those systems without forcing the wrong categories too early.

Unsupervised Machine Learning

Sat, 30 May 2026 00:00:00 +0000

This course introduces unsupervised machine learning as a practical framework for finding structure in complex data without predefined labels. Students work with clustering, dimensionality reduction, embeddings, matrix factorization, topic modeling, anomaly detection, graph representations, and model validation.

The course is designed for data science and computational social science applications: behavioral traces, text, networks, educational data, cultural data, organizations, and public-policy problems where the goal is to discover patterns, compare latent groups, and build interpretable representations.

Unsupervised Learning | CRiSS-LAB

Unsupervised learning for social systems

Unsupervised Machine Learning