My name is Arturo and I'm a highly caffeinated data scientist with 10 years of experience in the fields of tech and finance. I love training machine learning models from scratch and estimating causal effects from non-experimental data. In a nutshell, I use AI to figure out what will happen, and econometrics to understand why it's happening.
I work at @Google as a Behavioral Data Scientist and I also teach Econometrics at @ITAM.
I'm currently obsessed with transformers and multi-head attention mechanisms.
I recently developed a vanilla PySpark implementation of the Louvain algorithm for community detection as well as a module that uses message passing to automatically engineer graph-based features.
I've also made a few contributions to NetworkX, scikit-learn and GraphFrames in recent months.
Hope you enjoy your stay (;