Accuracy Convergent Field Predictors

TL;DR

This paper discusses field-based predictive algorithms capable of handling various data types and introduces methods to ensure their predictive accuracy converges, enhancing their reliability and performance.

Contribution

It introduces variants of field-based predictors and proposes adaptation methods to achieve predictive accuracy convergence.

Findings

Algorithms operate with categorical, continuous, and mixed data.

Methods for adapting algorithms to ensure accuracy convergence.

Discussion on predictive accuracy convergence as an evaluation criterion.

Abstract

Several predictive algorithms are described. Highlighted are variants that make predictions by superposing fields associated to the training data instances. They operate seamlessly with categorical, continuous, and mixed data. Predictive accuracy convergence is also discussed as a criteria for evaluating predictive algorithms. Methods are described on how to adapt algorithms in order to make them achieve predictive accuracy convergence.