Victor Coscrato

Victor Coscrato

Associate Professor - UFSCar | PhD in Artificial Intelligence

About

I am a teacher and researcher working at the intersection of statistics, machine learning, and artificial intelligence. I hold a Ph.D. in Artificial Intelligence from University College Cork and a Master's in Statistics from PIPGEs (USP/UFSCar). My research interests include recommendation systems, uncertainty quantification, and interpretable machine learning. I am passionate about teaching, open-source software, and statistical modeling.

Featured Publications

NLS: An accurate and yet easy-to-interpret prediction method – Neural Networks, 2023

V Coscrato, MHA Inácio, T Botari, R Izbicki

The NN-Stacking: Feature weighted linear stacking through neural networks – Neurocomputing, 2020

V Coscrato, MHA Inácio, R Izbicki

Agnostic tests can control the type I and type II errors simultaneously – Brazilian Journal of Probability and Statistics, 2020

V Coscrato, R Izbicki, RB Stern

Other Research

Uncertainty in Recommender Systems – Ph.D. Thesis, University College Cork, 2024

V Coscrato

Supplier Recommendation in Online Procurement – arXiv preprint, 2024

V Coscrato, D Bridge

Interpretable hypothesis tests – arXiv preprint, 2019

V Coscrato, LG Esteves, R Izbicki, RB Stern

Neural networks as an optimization tool for regression – Master's Dissertation, UFSCar/USP, 2019

V Coscrato

Teaching

2026/1

2025/2

Lecture Notes

Estatística Multivariada

Lecture notes for my Multivariate Statistics course (in Portuguese).

Access the book →

Redes Neurais com PyTorch

Lecture notes for my Neural Networks with PyTorch course.

Coming soon

Contact

You can reach me in Portuguese, English, or Spanish.

vcoscrato [at] gmail [dot] com

vcoscrato [at] ufscar [dot] br