Skip to content
View ledmaster's full-sized avatar

Block or report ledmaster

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ledmaster/README.md

👋 Hi, I am Mario Filho

I'm a self-taught machine learning geek who's turned a fascination with computer science into a pretty cool career.

My story kicked off with Andrew Ng's course, which got me hooked on machine learning.

Sure, I didn't know what a derivative was at first, and math and I weren't exactly best friends, but I dove headfirst into the challenge anyway.

Without a traditional background, I knew I needed to prove myself.

So, I decided to jump into the competitive world of Kaggle.

It was tough, but I loved every minute of it.

I ended up winning a few competitions, becoming a Kaggle Competitions Grandmaster, and even made it to the 12th spot in the global rankings out of over 180,000 data scientists.

This success opened up some amazing opportunities.

I landed the role of Lead Data Scientist at Upwork Inc., where I got to develop a pretty neat reranking system that improved how we qualified freelancers on the platform.

As a freelancer myself, I've worked on some exciting projects, like creating machine learning models for startups and Fortune 500 companies.

One of my favorites was developing an artwork pricing model for an art analysis startup.

But it's not all about work for me. I love sharing what I've learned with others.

I've been a content advisor at UC Berkeley's Data-X, authored a popular book called "Manual Prático de Data Science," and even created an online course where I taught more than 900 students how to build machine learning pipelines with Python.

On my YouTube channel I've been sharing free lessons on data science and machine learning in Portuguese, and we've built a community of over 23,000 subscribers.

This blog is my latest project in this educational journey.

I believe my unconventional learning journey has its perks. It's made me more open-minded and willing to experiment, always on the lookout for what works best in practice.

This approach has served me well so far and I'm excited to see where it'll take me next.

TL;DR

Pinned Loading

  1. tw-bert tw-bert Public

    Implementation of End-to-End Query Term Weighting (TW-BERT)

    Python 29 1

  2. gpt-summarizer gpt-summarizer Public

    A scrappy Jupyter notebook to summarize long podcasts, youtube videos, etc

    Jupyter Notebook 27 4

  3. unified-embeddings unified-embeddings Public

    Implementation of Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems

    Python 11 2

  4. meli2020 meli2020 Public

    9th (public) place solution to MeLi Data Challenge 2020

    Jupyter Notebook 23 3

  5. swing swing Public

    Implementation of the Swing Algorithm for Substitute Product Recommendation in Python

    Python 5

  6. How To Predict Multiple Time Series ... How To Predict Multiple Time Series With Scikit-Learn (With a Sales Forecasting Example)
    1
    {
    2
     "cells": [
    3
      {
    4
       "cell_type": "markdown",
    5
       "metadata": {},