Jason2Brownlee/MachineLearningMischief

Machine Learning Mischief: Examples from the dark side of data science

31
/ 100
Emerging

This project offers clear demonstrations of how machine learning experiments can be intentionally manipulated to show misleadingly good results. It illustrates methods like 'cherry-picking' data or 'p-hacking' statistical tests to achieve a desired outcome. This is for anyone who reviews, manages, or is new to machine learning projects and needs to understand how to identify unreliable or fraudulent results.

Use this if you need to learn how to spot unethical manipulation of machine learning project results, or if you're a junior data scientist who needs to understand what practices to avoid.

Not ideal if you're looking for best practices or tools to improve the rigor and quality of your machine learning experiments, as this focuses on demonstrating manipulative techniques.

data-science-ethics research-integrity model-evaluation statistical-fraud experimental-design
No License No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

59

Forks

5

Language

License

Last pushed

Oct 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Jason2Brownlee/MachineLearningMischief"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.