A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric

Regression, a supervised machine learning approach, establishes relationships between independent variables and a continuous dependent variable. It is widely applied in areas like price prediction and time series forecasting. The performance of regression models is typically assessed using error met...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad B. Hassanat, Mohammad Khaled Alqaralleh, Ahmad S. Tarawneh, Khalid Almohammadi, Maha Alamri, Abdulkareem Alzahrani, Ghada A. Altarawneh, Rania Alhalaseh
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/22/3623
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153098178854912
author Ahmad B. Hassanat
Mohammad Khaled Alqaralleh
Ahmad S. Tarawneh
Khalid Almohammadi
Maha Alamri
Abdulkareem Alzahrani
Ghada A. Altarawneh
Rania Alhalaseh
author_facet Ahmad B. Hassanat
Mohammad Khaled Alqaralleh
Ahmad S. Tarawneh
Khalid Almohammadi
Maha Alamri
Abdulkareem Alzahrani
Ghada A. Altarawneh
Rania Alhalaseh
author_sort Ahmad B. Hassanat
collection DOAJ
description Regression, a supervised machine learning approach, establishes relationships between independent variables and a continuous dependent variable. It is widely applied in areas like price prediction and time series forecasting. The performance of regression models is typically assessed using error metrics such as the Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). However, these metrics present challenges including sensitivity to outliers (notably MSE and RMSE) and scale dependency, which complicates comparisons across different models. Additionally, traditional metrics sometimes yield values that are difficult to interpret across various problems. Consequently, there is a need for a metric that consistently reflects regression model performance, independent of the problem domain, data scale, and outlier presence. To overcome these shortcomings, this paper introduces a new regression accuracy measure based on the Hassanat distance, a non-convex distance metric. This measure is not only invariant to outliers but also easy to interpret as it provides an accuracy-like value that ranges from 0 to 1 (or 0–100%). We validate the proposed metric against traditional measures across multiple benchmarks, demonstrating its robustness under various model scenarios and data types. Hence, we suggest it as a new standard for assessing regression models’ accuracy.
format Article
id doaj-art-c2a45180b6bf4794981a27d8bc8ad511
institution Kabale University
issn 2227-7390
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-c2a45180b6bf4794981a27d8bc8ad5112024-11-26T18:12:04ZengMDPI AGMathematics2227-73902024-11-011222362310.3390/math12223623A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance MetricAhmad B. Hassanat0Mohammad Khaled Alqaralleh1Ahmad S. Tarawneh2Khalid Almohammadi3Maha Alamri4Abdulkareem Alzahrani5Ghada A. Altarawneh6Rania Alhalaseh7Faculty of Information Technology, Mutah University, Karak 61710, JordanFaculty of Information Technology, Mutah University, Karak 61710, JordanFaculty of Information Technology, Mutah University, Karak 61710, JordanDepartment of Computer Science, Applied College, University of Tabuk, Tabuk 47512, Saudi ArabiaDepartment of Systems and Networking, Faculty of Computing and Information, Al-Baha University, Al-Baha 65779, Saudi ArabiaDepartment of Computer Science, Faculty of Computing and Information, Al-Baha University, Al-Baha 65779, Saudi ArabiaFaculty of Business, Mutah University, Karak 61710, JordanFaculty of Information Technology, Mutah University, Karak 61710, JordanRegression, a supervised machine learning approach, establishes relationships between independent variables and a continuous dependent variable. It is widely applied in areas like price prediction and time series forecasting. The performance of regression models is typically assessed using error metrics such as the Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). However, these metrics present challenges including sensitivity to outliers (notably MSE and RMSE) and scale dependency, which complicates comparisons across different models. Additionally, traditional metrics sometimes yield values that are difficult to interpret across various problems. Consequently, there is a need for a metric that consistently reflects regression model performance, independent of the problem domain, data scale, and outlier presence. To overcome these shortcomings, this paper introduces a new regression accuracy measure based on the Hassanat distance, a non-convex distance metric. This measure is not only invariant to outliers but also easy to interpret as it provides an accuracy-like value that ranges from 0 to 1 (or 0–100%). We validate the proposed metric against traditional measures across multiple benchmarks, demonstrating its robustness under various model scenarios and data types. Hence, we suggest it as a new standard for assessing regression models’ accuracy.https://www.mdpi.com/2227-7390/12/22/3623regressionmachine learningperformance assessmentHassanat distance
spellingShingle Ahmad B. Hassanat
Mohammad Khaled Alqaralleh
Ahmad S. Tarawneh
Khalid Almohammadi
Maha Alamri
Abdulkareem Alzahrani
Ghada A. Altarawneh
Rania Alhalaseh
A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric
Mathematics
regression
machine learning
performance assessment
Hassanat distance
title A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric
title_full A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric
title_fullStr A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric
title_full_unstemmed A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric
title_short A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric
title_sort novel outlier robust accuracy measure for machine learning regression using a non convex distance metric
topic regression
machine learning
performance assessment
Hassanat distance
url https://www.mdpi.com/2227-7390/12/22/3623
work_keys_str_mv AT ahmadbhassanat anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT mohammadkhaledalqaralleh anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT ahmadstarawneh anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT khalidalmohammadi anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT mahaalamri anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT abdulkareemalzahrani anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT ghadaaaltarawneh anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT raniaalhalaseh anoveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT ahmadbhassanat noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT mohammadkhaledalqaralleh noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT ahmadstarawneh noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT khalidalmohammadi noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT mahaalamri noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT abdulkareemalzahrani noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT ghadaaaltarawneh noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric
AT raniaalhalaseh noveloutlierrobustaccuracymeasureformachinelearningregressionusinganonconvexdistancemetric