Antonio Aguirre Data Modeling | Bayesian Statistics | Machine Learning

Antonio Aguirre

Welcome

Hello! I'm Antonio Aguirre, a Ph.D. candidate in Statistics at the University of California, Santa Cruz. I work with Dr. Bruno Sansó and Dr. Raquel Prado on Bayesian time series forecasting and quantile modeling, with a focus on uncertainty quantification and scalable variational inference.

I develop modern statistical and machine learning methods for forecasting, including Deep Echo State Networks (Deep ESN). I also have industry experience running experiment workflows and automated backtests on AWS.

I hold a B.Sc. in Applied Mathematics and an M.Sc. in Economics from Instituto Tecnológico Autónomo de México (ITAM).

Research Interests

  • Time Series Forecasting: Bayesian dynamic models for probabilistic prediction and decision support.
  • Quantile Modeling and Risk Assessment: Quantile-based methods for calibration and extremes.
  • Scalable Bayesian Inference: Variational Bayes and approximate inference for large, complex models.
  • Continual Learning: Online updates and adaptive forecasting as new data arrive.
  • Forecast Combination: Multi-model synthesis and bias correction for operational forecasts.

Real-Time Monitoring: San Lorenzo River Discharge

Note: Live discharge at Big Trees with a short-range forecast overlay when available.
Loading data...
Data source: USGS NWIS IV | Forecast overlay: NWS/NWM ensembles | Flood thresholds: discharge-based (approx.)