Survey of expert opinion: Which machine learning method may be used for which task?

Publisher Website
Google Scholar
Abstract
Determining the most appropriate Machine Learning (ML) method, system, or algorithm for a particular application is not trivial. This article reports on a survey of 103 experts specializing in ML who were asked to rate ML method appropriateness to intelligent tasks. Ratings were captured via a structured questionnaire including 12 ML methods and 9 task categories. Results showed that the experts mapped particular ML methods to task categories. Factor analysis revealed three fundamental factors, which explained most of the variance in the expert ratings. Machine learning methods could be grouped on the basis of these factors into six application categories, wherein one or more methods were deemed most appropriate by the evaluated group of experts. This, in turn, concludes that cooperation between alternative ML methods may be necessary to support one or more intelligent tasks.

This publication has 24 references indexed in Scilit: