Explainable Online Validation of Machine Learning Models for Practical Applications

TL;DR

This paper introduces an explainable online validation method for machine learning models, simplifying validation using training data and focusing on interpretability, with a new conditional probability-based algorithm that is memory-efficient.

Contribution

The paper proposes a novel, explainable validation approach for ML models that is online-capable and more memory-efficient than traditional methods like kNN.

Findings

The conditional probability-based validation algorithm is online-capable.

The new method requires less memory than kNN.

The approach performs well on multiple datasets and problems.

Abstract

We present a reformulation of the regression and classification, which aims to validate the result of a machine learning algorithm. Our reformulation simplifies the original problem and validates the result of the machine learning algorithm using the training data. Since the validation of machine learning algorithms must always be explainable, we perform our experiments with the kNN algorithm as well as with an algorithm based on conditional probabilities, which is proposed in this work. For the evaluation of our approach, three publicly available data sets were used and three classification and two regression problems were evaluated. The presented algorithm based on conditional probabilities is also online capable and requires only a fraction of memory compared to the kNN algorithm.