JSM talk: dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python

Slides: PDF

Personal:

• My website: hbaniecki.com
• MI2 lab’s website: mi2.ai

dalex:

• Website: dalex.drwhy.ai
• GitHub: github.com/ModelOriented/DALEX
• START here: python.drwhy.ai

Papers:

• dalex in Python (JMLR, 2021): jmlr.org/papers/v22/20-1473.html
• DALEX in R (JMLR, 2018): jmlr.org/papers/v19/18-416.html

Books:

• Explanatory Model Analysis: Explore, Explain, and Examine Predictive Models (Chapman and Hall/CRC, 2021): ema.drwhy.ai
• The Hitchhiker’s Guide to Responsible Machine Learning (2022): rml.mi2.ai

Tutorials (in R):

• Introduction to Responsible Machine Learning (useR! 2022): github.com/MI2DataLab/ResponsibleML-UseR2022
• Introduction to Responsible Machine Learning (useR! 2021): github.com/MI2DataLab/ResponsibleML-UseR2021

Congratulations to Vittorio Orlandi (Duke University) for the Award’s honorable mention, for the R package FLAME: interpretable matching methods for performing causal inference on observational data with discrete covariates.

Many thanks to:

• Award’s organizers and the review panel: Raymond Wong (Texas A&M University), Yixuan Qiu (Shanghai University of Finance and Economics), Samantha Tyner (Tritura), Philip Waggoner (YouGov America, Northwestern University, University of Virginia).

• Przemysław Biecek

• Wojciech Kretowicz, Mateusz Krzyziński, Piotr Piątyszek, Jakub Wiśniewski, Artur Żółkowski

• Faculty of Mathematics and Information Science, Warsaw University of Technology

• National Science Centre (Poland) grants No. 2017/27/B/ST6/01307 and 2019/34/E/ST6/00052