Metadata-Version: 2.1
Name: axa_safeai
Version: 0.1.1
Summary: MODEL AGNOSTIC SAFE AI package to measure risks of AI models WITHOUT CONSIDERING TYPE OF THE MODEL
Author: Golnoosh Babaei
Author-email: <golnoosh.babaei@unipv.it>
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: Unix
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: Microsoft :: Windows
Description-Content-Type: text/markdown
License-File: LICENSE

### AXA safeAI package

This S.A.F.E. approach is based on “Rank Graduation
Box” proposed in [Babaei et al. 2024](https://www.sciencedirect.com/science/article/pii/S0957417424021067). The use of the term “box” is motivated by the need of emphasizing that our proposal is
always in progress so that, like a box, it can be constantly filled by innovative tools addressed
to the measurement of the new future requirements necessary for the safety condition of
AI-systems.

# Install

Simply use:

pip install axa_safeai

# Citations

The proposed measures in this package came primarily out of research by 
[Paolo Giudici](https://www.linkedin.com/in/paolo-giudici-60028a/), [Emanuela Raffinetti](https://www.linkedin.com/in/emanuela-raffinetti-a3980215/), 
and [Golnoosh Babaei](https://www.linkedin.com/in/golnoosh-babaei-990077187/) in the [Statistical laboratory](https://sites.google.com/unipv.it/statslab-pavia/home?authuser=0) 
at the University of Pavia. 

This package is based on the following papers:
* [Babaei, G., Giudici, P., & Raffinetti, E. (2024). A Rank Graduation Box for SAFE AI. Expert Systems with Applications, 125239.](https://doi.org/10.1016/j.eswa.2024.125239)
* [Giudici, P., & Raffinetti, E. (2024). RGA: a unified measure of predictive accuracy. Advances in Data Analysis and Classification, 1-27.](https://link.springer.com/article/10.1007/s11634-023-00574-2)
* [Raffinetti, E. (2023). A rank graduation accuracy measure to mitigate artificial intelligence risks. Quality & Quantity, 57(Suppl 2), 131-150.](https://link.springer.com/article/10.1007/s11135-023-01613-y)
