Camilo Maldonado Vidal

Data Scientist with a Master of Science in Computer Engineering from UTFSM, with experience in both industry and applied research. His main area of expertise is Natural Language Processing (NLP) and deep learning.

He has worked on the design and implementation of robust textual classification models, especially in contexts where data present noise, ambiguity or out-of-distribution instances.

His most recent research, entitled "Beta Distribution Approach for Outlier Exposure in Multi-class Text Classification" (available at https://doi.org/10.1007/978-3-031-76607-7_15), proposes a statistical approach to improve the detection of unseen classes and informative data in open-world classification scenarios, contributing to more adaptive and reliable systems.