Challenges Towards Production-Ready Explainable Machine Learning

Website Maintenance Alert

Due to scheduled maintenance, the USENIX website may not be available on Monday, March 17, from 10:00 am–6:00 pm Pacific Daylight Time (UTC -7). We apologize for the inconvenience and thank you for your patience.

If you would like to register for NSDI '25, SREcon25 Americas, or PEPR '25, please complete your registration before or after this time period.

Authors: 

Lisa Veiber, Kevin Allix, Yusuf Arslan, Tegawendé F. Bissyandé, and Jacques Klein, SnT – Univ. of Luxembourg

Abstract: 

Machine Learning (ML) is increasingly prominent in organizations. While those algorithms can provide near perfect accuracy, their decision-making process remains opaque. In a context of accelerating regulation in Artificial Intelligence (AI) and deepening user awareness, explainability has become a priority notably in critical healthcare and financial environments. The various frameworks developed often overlook their integration into operational applications as discovered with our industrial partner. In this paper, explainability in ML and its relevance to our industrial partner is presented. We then discuss the main challenges to the integration of explainability frameworks in production we have faced. Finally, we provide recommendations given those challenges.

OpML '20 Open Access Sponsored by NetApp

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX

Presentation Video 
Teaser
Full