Projects per year
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.
Original language | English |
---|---|
Title of host publication | 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2021 |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
ISBN (Electronic) | 978-1-6654-9552-3 |
ISBN (Print) | 978-1-6654-9553-0 |
DOIs | |
Publication status | E-pub ahead of print - 1 Mar 2022 |
Event | The Asia-Pacific Conference on Computer Science and Data Engineering - Virtual, Brisbane, Australia Duration: 8 Dec 2021 → 10 Dec 2021 Conference number: 8 https://ieee-csde.org/2021/ |
Publication series
Name | 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering, CSDE 2021 |
---|
Conference
Conference | The Asia-Pacific Conference on Computer Science and Data Engineering |
---|---|
Abbreviated title | IEEE CSDE 2021 |
Country/Territory | Australia |
City | Brisbane |
Period | 8/12/21 → 10/12/21 |
Internet address |
Bibliographical note
Funding Information:ACKNOWLEDGMENT This work was supported by Innovate UK Knowledge Transfer Partnership between University of Bristol and Claritum Limited (KTP 11952).
Publisher Copyright:
© IEEE 2022.
Keywords
- Spend management
- AI service
- Model deployment
- ML development pipeline
- Support vector machine
Fingerprint
Dive into the research topics of 'AgileML: A Machine Learning Project Development Pipeline Incorporating Active Consumer Engagement'. Together they form a unique fingerprint.Projects
- 1 Finished