EVALUATION OF THE CONFIDENCE INTERVAL FOR DECISION PREDICTION OF AN ENSEMBLE OF CLASSIFIERS
“STC-Innovation”, Saint Petersburg, 196084, Russian Federation; ITMO University, Saint Petersburg, 197101, Russian Federation; Chief Scientific Officer, Head of the Chair
Abstract. An algorithm is proposed for evaluation of the confidence interval for decision prediction of an ensemble of classifiers, where each classifier in the ensemble returns a prediction as a logarithmic likelihood ratio.
Keywords: confidence interval, decision prediction, ensemble of classifiers, speaker identification, voice biometric system