My research career spans over 150 published articles across three decades, moving from astrophysics through data science to business analytics. The unifying theme has been developing and applying advanced computational methods—particularly machine learning and artificial intelligence—to extract insights from complex systems, whether astronomical surveys, cosmological simulations, or financial markets.

Research Areas

Business Analytics & Financial Markets (2017-Present)
Applying multimodal deep learning to earnings calls analysis, graph neural networks to financial market networks, and information-theoretic approaches to market efficiency and industry recovery patterns. Current work explores how AI and emerging technologies reshape accounting, audit, and financial decision-making.

Data Science & Machine Learning (2014-2017)
Developed breakthrough techniques including the Extended Isolation Forest algorithm for anomaly detection,EIF GitHub ensemble machine learning methods using random forests and self-organizing maps,SOM GitHub deep convolutional neural networks for classification tasks, sparse representation techniques for probability density functions,SparsePz GitHub and information-theoretic measures.PyIF GitHub

Astrophysics & Computational Cosmology (1997-2017)
Twenty years developing machine learning methods for massive astronomical datasets. Co-founded the Dark Energy Survey, pioneered GPU applications in cosmology, and created algorithms for photometric redshift estimation and star-galaxy classification.Received the 2021 ACM SIGMOD Systems Award for contributions to the Sloan Digital Sky Survey.

Working papers and selected publications →