Toward Best Practices for Explainable B2B Machine Learning

Kit Kuksenok

Toward Best Practices for Explainable B2B Machine Learning

Human-Computer Interaction 2019-06-13 v1 Artificial Intelligence

Authors: Kit Kuksenok

Abstract

To design tools and data pipelines for explainable B2B machine learning (ML) systems, we need to recognize not only the immediate audience of such tools and data, but also (1) their organizational context and (2) secondary audiences. Our learnings are based on building custom ML-based chatbots for recruitment. We believe that in the B2B context, "explainable" ML means not only a system that can "explain itself" through tools and data pipelines, but also enables its domain-expert users to explain it to other stakeholders.

Keywords

explainable artificial intelligence unified modeling language interpretable machine learning

Cite

@article{arxiv.1906.04837,
  title  = {Toward Best Practices for Explainable B2B Machine Learning},
  author = {Kit Kuksenok},
  journal= {arXiv preprint arXiv:1906.04837},
  year   = {2019}
}

Comments

4 pages, 1 figure; position paper for INTERACT 2019 workshop on Humans in the Loop: Bridging AI and HCI

Related papers

View all related →