Viewing profile — tabacof

I wrote two blog posts based on my experience betting on CS:GO in 2019. The first post covers the following topics: * What is your edge? * Financial decision-making with ML * One b…

This post covers the foundations of e-sports betting with machine learning: financial decision-making, expected profits of a bet, multiple bets with the Kelly criterion, probabilit…

I started this blog recently, though some posts were written a few years ago (one even reached HN front page!): https://tabacof.github.io/

I wrote the blog post above based on the learnings I had when creating a MLOps solution using AWS Lambda for machine learning model deployment. Tl;dr: The post shows how to deploy …

In this blog post, I explore the problem of name classification with ChatGPT and 3 ML models of increasing complexity (logistic regression, FastAI LSTM, and HuggingFace DistilBERT)…

Hi Soneca, I am also a Brazilian starting two very modest side business intending to sell to international customers: 1) https://www.deploir.com 2) https://www.whoworth.com What a …

>Spark is a terribly inefficient solution to any known/stable data processing or analytics jobs. Can you expand on that?

Latin America is very unsafe. The list of top 50 cities by murder rate is very telling: https://en.wikipedia.org/wiki/List_of_cities_by_murder_rate I have lived most of my life in …

This is insane, this judge must be on a power trip. WhatsApp is now part of Brazilian social life and economy. Everyone here is part of many groups of friends, family or workmates,…

Causality is a bit harder to integrate with current machine learning models as it's hard even with standard probabilistic graphical models. On the other hand, there has been a lot …

Torch7 has amazing GPU support. If you wanna send a tensor (array) to the GPU, you just type array:cuda(). All operations you do from now on will be on the GPU. More involved examp…