A SIGNIFICANT INCREASE in the adoption of machine learning (ML) in business has led to the emergence of ML-enabled systems. Although this is the case, ML-enabled systems introduce additional challenges, which has resulted in many systems being shelved as opposed to being deployed in production. Lately, practitioners and the academic research community have been working toward identifying and solving some of those challenges related to ML development, deployment, and testing. This article highlights key challenges faced by FMS to incorporate agile for development of Proktor, describes the Agile4MLS methodology adopted by us, and further provides key lessons learned and takeaways to the community based on an internal validation study.
Agile4MLS-Leveraging Agile Practices for Developing Machine Learning-Enabled Systems An Industrial Experience
Vaidhyanathan, K;Muccini, H
Membro del Collaboration Group
;
2022-01-01
Abstract
A SIGNIFICANT INCREASE in the adoption of machine learning (ML) in business has led to the emergence of ML-enabled systems. Although this is the case, ML-enabled systems introduce additional challenges, which has resulted in many systems being shelved as opposed to being deployed in production. Lately, practitioners and the academic research community have been working toward identifying and solving some of those challenges related to ML development, deployment, and testing. This article highlights key challenges faced by FMS to incorporate agile for development of Proktor, describes the Agile4MLS methodology adopted by us, and further provides key lessons learned and takeaways to the community based on an internal validation study.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
