Number of Instances for Reliable Feature Ranking in a Given Problem
Background: In practical use of machine learning models, users may add new features to an existing classification model, reflecting their (changed) empirical understanding of a field. New features potentially increase classification accuracy of the model or improve its interpretability. Objectives:...
Main Authors: | Bohanec Marko, Borštnar Mirjana Kljajić, Robnik-Šikonja Marko |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2018-07-01
|
Series: | Business Systems Research |
Subjects: | |
Online Access: | https://doi.org/10.2478/bsrj-2018-0017 |
Similar Items
-
Estimation of minimum sample size for identification of the most important features: a case study providing a qualitative B2B sales data set
by: Marko Bohanec, et al.
Published: (2017-01-01) -
Organizational Learning Supported by Machine Learning Models Coupled with General Explanation Methods: A Case of B2B Sales Forecasting
by: Bohanec Marko, et al.
Published: (2017-08-01) -
Enumerative feature subset based ranking system for learning to rank in presence of implicit user feedback
by: Mohd Wazih Ahmad, et al.
Published: (2020-10-01) -
A feature selection method with feature ranking using genetic programming
by: Guopeng Liu, et al.
Published: (2022-12-01) -
Feature ranking and rank aggregation for automatic sleep stage classification: a comparative study
by: Shirin Najdi, et al.
Published: (2017-08-01)