Human-Centric-Machine-Learning/improve-expert-predictions-conformal-prediction

Code for "Improving Expert Predictions with Conformal Prediction" , ICML 2023

28
/ 100
Experimental

This project helps scientists, medical professionals, or analysts who rely on expert judgments combined with machine learning models to make better-informed decisions. It takes initial predictions from an expert and data from a machine learning model, then combines them to provide more reliable, calibrated predictions, often expressed with a confidence level or prediction range. This is for professionals who need to quantify uncertainty and improve the accuracy of human-AI collaboration.

No commits in the last 6 months.

Use this if you need to systematically improve the reliability of decisions made by combining human expertise with machine learning predictions, especially when you need to understand the confidence level of those combined judgments.

Not ideal if you are looking for a standalone machine learning model or if your primary goal is to evaluate the raw performance of an expert or a model in isolation, rather than their collaborative improvement.

decision-support predictive-analytics human-in-the-loop-AI uncertainty-quantification expert-systems
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

13

Forks

4

Language

Jupyter Notebook

License

Last pushed

Aug 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Human-Centric-Machine-Learning/improve-expert-predictions-conformal-prediction"

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