AgileML: A Machine Learning Project Development Pipeline Incorporating Active Consumer Engagement

Abstract

Machine learning (ML) project deployments often have long lead times and may face delays or failures due to lack of data, poor data quality, and data drift. To address these problems, we introduce AgileML, a novel machine learning product development lifecycle where the end consumer and development team work collaboratively through an iterative process of development. We use AgileML to develop a commercial spend classification service and demonstrate that the earliest alpha deployment can offer users significant commercial value. User-testing with a professional spend analyst demonstrates that the system can lead to a five-fold increase in classification speed.