Quadratic Multiform Separation: A New Classification Model in Machine Learning

TL;DR

This paper introduces a novel classification model that achieves comparable accuracy to existing methods, runs faster, and can identify subsets of samples with higher predictive accuracy, with patents pending.

Contribution

The paper presents a new classification model that improves speed and the ability to identify high-confidence samples, with patent protection pending.

Findings

Comparable predictive accuracy to common models

Significantly faster runtime

Ability to identify high-accuracy subsets of samples

Abstract

In this paper we present a new classification model in machine learning. Our result is threefold: 1) The model produces comparable predictive accuracy to that of most common classification models. 2) It runs significantly faster than most common classification models. 3) It has the ability to identify a portion of unseen samples for which class labels can be found with much higher predictive accuracy. Currently there are several patents pending on the proposed model.