I'm a physicist with a Ph.D. in theoretical particle physics, now transitioning into data science with a strong focus on NLP, machine learning, and statistical modeling. I enjoy solving complex problems, visualizing insights, and building meaningful tools powered by data.
- Build data pipelines and exploratory analyses in Python and R
- Work with NLP tasks: tokenization, stemming, lemmatization, n-gram models
- Develop machine learning models using scikit-learn, exploring PyTorch and TensorFlow
- Simulate physical systems using finite elements, symbolic math, and scientific computing
- Document everything in Jupyter and RMarkdown, with reproducibility as a priority
-
Sentiment Analysis on IMDB Reviews (R)
NLP analysis, preprocessing, stemming/lemmatization, n-grams, visualizations and future model deployment. -
Fraud Detection with ML (Python)
Binary classification project using imbalanced datasets, feature engineering, and performance metrics.
Python
| R
| Jupyter
| Pandas
| NumPy
| scikit-learn
| ggplot2
| tidytext
| Docker
| Git
| Linux
- Remote roles in Data Science, ML, or NLP
- Junior / Entry-level opportunities with learning potential
- Projects or research collaborations with real-world impact
- GitHub: @alexmatiasas
- LinkedIn: linkedin.com/in/alexmatiasastorga
- Portfolio: alexmatiasas.github.io
"Bridging science and data to build smarter tools and better insights."