Skip to content
View ergodicdev's full-sized avatar
  • Lima, Perù

Block or report ergodicdev

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
ergodicdev/README.md
ergodicdev banner

> Exploring the full state space of machine learning

Data Science & Artificial Intelligence · Lima, Perú 🇵🇪

A system is ergodic when its time average equals its space average.
I apply that same principle to learning — covering the full solution space.

About me

I'm a Data Scientist and ML Engineer currently pursuing a Master's degree in Data Science & Artificial Intelligence. My thesis project NextStopAI applies deep learning to transit stop prediction, with full experiment tracking via MLflow and model registry on Databricks.

I believe in reproducible research, clean pipelines, and understanding the math behind every model — not just running .fit().

Tech Stack

Python PyTorch MLflow Databricks Jupyter Pandas NumPy Scikit--learn Git GitHub

Thesis Project — NextStopAI

NextStopAI is a deep learning system for transit stop prediction built as part of my Master's thesis.

Pipeline:

  • 01_curation.ipynb — Data ingestion, cleaning & feature engineering
  • 02_training.ipynb — Model training with MLflow experiment tracking
  • 03_inference.ipynb — Massive inference & Databricks model registry

Key tools: PyTorch · MLflow · Databricks · Pandas · NumPy

 
Transit Data
     │
     ▼
 Curación
     │
     ▼
 Entrenamiento ──► MLflow
     │
     ▼
 Inferencia ──► Databricks
     │
     ▼
  Predicción

NextStopAI

What is Ergodic Theory?

In mathematics, a dynamical system is ergodic if its time average equals its ensemble average.
In other words — a particle that visits every point in the state space eventually.

I chose this name because great data scientists don't get stuck in local minima.
They explore the full solution space.

GitHub Stats

Let's connect

Gmail Location

MSc Data Science & AI · Thesis 2025 · Built with curiosity and gradient descent

Pinned Loading

  1. NextStopAI NextStopAI Public

    Deep learning model for transit stop prediction using MLflow experiment tracking and Databricks model registry. Curación, entrenamiento e inferencia masiva.

    Python