Efficient crowdsourcing of unknown experts using bounded multi-armed bandits
- Submitting institution
-
University of Oxford
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2015
- Type
- D - Journal article
- DOI
-
10.1016/j.artint.2014.04.005
- Title of journal
- Artificial Intelligence
- Article number
- -
- First page
- 89
- Volume
- 214
- Issue
- -
- ISSN
- 0004-3702
- Open access status
- Out of scope for open access requirements
- Month of publication
- May
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 56
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes a novel multi-armed bandit (MAB) model with a bounded total arm-pulling budget, and applies it to solving the challenge faced by an organisation seeking to allocate tasks to crowd-workers. The paper presents an optimal algorithm for this setting. The algorithm is applied to real-world data from oDesk, a prominent expert crowdsourcing site, and is shown to improve upon the allocation approaches used in existing platforms. The paper has been influential (see for example the survey by Mao et al. in J. of Systems and Software 2017), and continues to inform research (see e.g. recent work in ICML�19).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -