Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Feature selection via coalitional game theory.

Shay Cohen1, Gideon Dror, Eytan Ruppin

  • 1School of Computer Sciences, Tel-Aviv University, Tel-Aviv, Israel. scohen@cs.cmu.edu

Neural Computation
|May 25, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Histopathology-inferred spatial transcriptomics characterizes the tumor microenvironment in 1,500 head and neck tumors and predicts clinical outcomes.

bioRxiv : the preprint server for biology·2026
Same author

Trials for Rare Cancers Are More Successful than those for Common Cancers.

ESMO rare cancers·2026
Same author

Liquid surrogates of spatial tumor ecosystems.

Cell research·2026
Same author

Longitudinal validation of ENLIGHT, an AI predictor of immunotherapy response and resistance, in pan-cancer cohorts.

NPJ precision oncology·2026
Same author

Author Correction: The ubiquitin ligase RNF5 determines acute myeloid leukemia growth and susceptibility to histone deacetylase inhibitors.

Nature communications·2026
Same author

SYNTHESIS-Breast: A prospective early-phase trial of a genetic-interaction- focused computational algorithm in advanced metastatic breast cancer.

Research square·2026
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

We introduce the Contribution-Selection Algorithm (CSA), a new method for feature selection. Its backward elimination variant achieved the highest accuracy across various datasets by using game theory to estimate feature usefulness.

Area of Science:

  • Computer Science
  • Machine Learning
  • Data Mining

Background:

  • Feature selection is crucial for improving model performance and interpretability.
  • Existing methods may not optimally identify relevant features for diverse datasets.
  • Game theory offers a robust framework for quantifying feature contributions.

Purpose of the Study:

  • To introduce and evaluate the Contribution-Selection Algorithm (CSA) for effective feature selection.
  • To leverage multi-perturbation Shapley analysis (MSA) for estimating feature usefulness.
  • To compare CSA's performance against established feature selection techniques.

Main Methods:

  • Developed the Contribution-Selection Algorithm (CSA) based on multi-perturbation Shapley analysis (MSA).
  • Implemented CSA with both forward selection and backward elimination strategies.

Related Experiment Videos

  • Optimized performance measures including accuracy, balanced error rate, and AUC on unseen data.

    • Main Results:

    • The backward elimination variant of CSA demonstrated superior classification accuracy compared to other methods.
    • CSA effectively estimates feature usefulness using game theory principles.
    • The algorithm showed robust performance across a diverse range of datasets.

    Conclusions:

    • CSA, particularly its backward elimination mode, is a highly effective feature selection algorithm.
    • The integration of game theory (MSA) enhances the estimation of feature utility.
    • CSA offers a promising approach for optimizing machine learning model performance.