Skip to content

Latest commit

 

History

6 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 

Repository files navigation

AI Autopsy: Hacking and Debugging Decisions with XAI

This repository contains the official code and presentation materials for the hands-on workshop presented at GDG Presidente Prudente - DevFest 2025 in .

About This Workshop

AI models are often "black boxes." They give us predictions but can't explain why. This is dangerous—it can lead to biased, unfair, and untrustworthy systems.

In this workshop, we perform an "autopsy" on a black-box model. We will:

  1. Train a high-performance classifier on the classic Titanic dataset.
  2. Debug its logic to understand why it predicts survival or death.
  3. Use powerful Explainable AI (XAI) techniques LIME and SHAP to make the model transparent.
  4. Generate powerful visualizations to explain individual predictions and global model behavior.

🚀 Get Started (Hands-On)

The easiest way to run the workshop code is by using Google Colab, which runs everything in your browser for free.

Just click the badge below!

Open In Colab

🛠️ Technologies & Concepts

  • Python 3
  • Libraries: scikit-learn, LightGBM, Pandas
  • XAI Tools: lime, shap
  • Dataset: The Titanic

Repository Contents

  • ai_autopsy_xai_titanic.ipynb: The main Google Colab notebook with all the hands-on code.
  • slides/: A directory containing the workshop presentation slides (e.g., in PDF format).

About the Speakers

  • Mateus Mendonça Monteiro: [MSc student and Backend Software Engineer at Luizalabs]
    • LinkedIn: linkedin.com/in/mateus-men
    • GitHub: github.com/mateusememe
  • Maria Beatriz França: [Data Scientist Lead in Vericode]
    • LinkedIn: linkedin.com/in/maria-beatriz-frança/
    • GitHub: github.com/mbsf

About

Code & materials for the "AI Autopsy" workshop at DevFest 2025. Learn to debug AI decisions using LIME and SHAP.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages