Development of a Risk Index for Viral Diseases using sociodemographic and landscape data.

Assisted the "Econometrics and Spatial Statistics" (Spring '24) course and the "Statistical Inference" (Fall '23) course. Duties included preparing coding sessions in R and Python, lecturing, grading, and tutoring.

Master of Science - MS, Statistical Computing (Data Science)Speaker and participant at various events. - DSC Datathon 2023 (ITESM). Detection of abnormal server behavior using consumption metrics from KIO Networks. My role was to develop a time series anomaly detection strategy. Analysis developed in Python. Our submit was selected as one of the best five. - 64th International Statistical Institute World Statistics Congress (ISI). Attended the FDA seminars and lectures of the congress.- XVII Industrial Problem Solving Workshop (CIMAT-Université de Montréal- FinML). Gas station optimal supply and sales forecasting for Harim Carburacion. My contribution was to conduct variable selection and proposed time series models to do short-term sales forecasting. Analysis developed in R. - DSC Datathon 2024 (ITESM). Generating business insights for data-driven decisions from tweets using NLP and LLMs for Hey Banco. Analysis developed in Python. Our work received an honorable mention.- XVll School on Probability and Statistics (UdeG-CIMAT). Presentation of poster 'Copula based Functional Quantile Regression to Estimate Particulate Matter at Metropolita Area of the Valley of Mexico'. Workshops and lectures on Probability, Statistics and Data Science.Relevant Coursework: Statistical Inference, Multivariate Statistics, Machine Learning, Time Series Analysis, Generalized Linear Models, Deep Learning.Granted with Conacyt Scholarship.

- Undergraduate Research Project (2021-12/3-357): "Machine Learning in High Energy Physics". Worked on jet recombination and classification in proton-proton (pp) collisions. - Reconstruction of quark and gluon jets from pp collisions using a recombination scheme (via clustering). Density estimation of the most representative kinematic features from each jet class. Application of classification methods (Multilayer Perceptrons, LDA, SVM, BDT) using the kinematic features in order to separate quark jets from gluon jets. For these purposes, ROOT (C++) was employed.- Since gluons radiate more than quarks, this classification task let us to identify radiation sources in pp collisions.