Muhammad Hasan Ferdous

Muhammad Hasan Ferdous is a Ph.D. candidate in Information Systems at the University of Maryland, Baltimore County (UMBC). His research focuses on robust causal discovery from autocorrelated, non-stationary multivariate time series, bridging the gap between theoretical guarantees and practical deployment in domains such as healthcare and climate.

Hasan develops methods that decompose temporal structure and leverage modern machine learning to identify stable, intervention-relevant causal relationships. His recent work includes CDANs and eCDANs for temporal causal discovery, decomposition-based causal discovery (DCD), and TimeGraph, a synthetic benchmark suite for stress-testing time-series causal discovery algorithms.

He has teaching experience across information systems and data management courses, including Management Information Systems, Database Program Development, Advanced Database Project, and Structured Systems Analysis and Design. Beyond research and teaching, he enjoys thinking about how causal AI can make real-world decision systems more robust and interpretable.