Output details
11 - Computer Science and Informatics
University of Bristol
Article title
A Unified View of Performance Metrics: Translating Threshold Choice into Expected Classification Loss
Type
D - Journal article
DOI
-
Title of journal
Journal of Machine Learning Research
Article number
-
Volume number
13
Issue number
Oct
First page of article
2813
ISSN of journal
1532-4435
Year of publication
2012
Number of additional authors
2
Additional information
<24> This paper, which shows how to derive several hitherto unknown but fundamental relationships between performance metrics in machine learning, is the culmination of over five years work by Flach and others. The paper resulted in a successful grant application to the CHIST-ERA programme (EPSRC EP/K018728/1 for £381,274 from 02/2013 - 01/2016 , total grant value €938,577 for three partners, with partners from France and Spain, on model reuse in data mining.
Interdisciplinary
-
Cross-referral requested
-
Research group
B - Intelligent Systems Laboratory
Citation count
2
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
