New Metric Formulas that Include Measurement Errors in Machine Learning for Natural Sciences

TL;DR

This paper introduces new formulas for evaluating machine learning models that explicitly incorporate measurement errors in data, providing more realistic performance estimates especially in physics and sciences.

Contribution

It derives general, model-independent formulas for common metrics that account for measurement errors, improving the reliability of model evaluation in scientific data analysis.

Findings

Formulas provide more pessimistic, realistic metric estimates.

Applicable to both regression and classification problems.

Valid for any measurement error type and data model.

Abstract

The application of machine learning to physics problems is widely found in the scientific literature. Both regression and classification problems are addressed by a large array of techniques that involve learning algorithms. Unfortunately, the measurement errors of the data used to train machine learning models are almost always neglected. This leads to estimations of the performance of the models (and thus their generalisation power) that is too optimistic since it is always assumed that the target variables (what one wants to predict) are correct. In physics, this is a dramatic deficiency as it can lead to the belief that theories or patterns exist where, in reality, they do not. This paper addresses this deficiency by deriving formulas for commonly used metrics (both for regression and classification problems) that take into account measurement errors of target variables. The new formulas give an estimation of the metrics which is always more pessimistic than what is obtained with the classical ones, not taking into account measurement errors. The formulas given here are of general validity, completely model-independent, and can be applied without limitations. Thus, with statistical confidence, one can analyze the existence of relationships when dealing with measurements with errors of any kind. The formulas have wide applicability outside physics and can be used in all problems where measurement errors are relevant to the conclusions of studies.